📄 sharpictclas分词系统简介(1)读取词典库 - first we try, then we trust - 博客园.mht
字号:
<BR> }=20
<BR> } <BR> =
<SPAN=20
style=3D"COLOR: #0000ff">catch</SPAN> (<SPAN=20
style=3D"COLOR: #808000">Exception</SPAN> e) =
<BR> {=20
<BR> =20
Console.WriteLine(e.Message);=20
<BR> isSuccess =3D <SPAN =
style=3D"COLOR: #0000ff">false</SPAN>; =
<BR> }=20
<BR> <SPAN style=3D"COLOR: =
#0000ff">finally</SPAN>=20
<BR> {=20
<BR> <SPAN=20
style=3D"COLOR: #0000ff">if</SPAN> (binReader !=3D <SPAN=20
style=3D"COLOR: #0000ff">null</SPAN>)=20
<BR> =20
binReader.Close(); =
<BR><BR> =20
<SPAN style=3D"COLOR: #0000ff">if</SPAN> (fileStream !=3D <SPAN=20
style=3D"COLOR: #0000ff">null</SPAN>)=20
<BR> =20
fileStream.Close(); <BR> }=20
<BR> <SPAN style=3D"COLOR: =
#0000ff">return</SPAN>=20
isSuccess; <BR> } <BR> <SPAN=20
style=3D"COLOR: #008000">//...... </SPAN><BR>} <BR><BR></DIV></DIV>
<P>=E4=B8=8B=E9=9D=A2=E5=86=85=E5=AE=B9=E8=8A=82=E9=80=89=E8=87=AA=E8=AF=8D=
=E5=BA=93=E4=B8=ADCCID=E4=B8=BA2=E3=80=813=E3=80=814=E3=80=815=E7=9A=84=E5=
=8D=95=E5=85=83=EF=BC=8C=20
CCID=E7=9A=84=E5=8F=96=E5=80=BC=E8=8C=83=E5=9B=B4=E8=87=AA1=EF=BD=9E6768=EF=
=BC=8C=E5=AF=B9=E5=BA=946768=E4=B8=AA=E6=B1=89=E5=AD=97=EF=BC=8C=E6=89=80=
=E6=9C=89=E4=B8=8E=E8=AF=A5=E6=B1=89=E5=AD=97=E5=8F=AF=E4=BB=A5=E7=BB=84=E6=
=88=90=E7=9A=84=E8=AF=8D=E5=9D=87=E8=AE=B0=E5=BD=95=E5=9C=A8=E7=9B=B8=E5=BA=
=94=E7=9A=84=E5=8D=95=E5=85=83=E5=86=85=E3=80=82=E8=AF=8D=E5=BA=93=E4=B8=AD=
=E8=AE=B0=E5=BD=95=E7=9A=84=E8=AF=8D=E6=98=AF=E6=B2=A1=E6=9C=89=E9=A6=96=E6=
=B1=89=E5=AD=97=E7=9A=84=EF=BC=88=E6=88=91=E7=94=A8=E5=B8=A6=E6=8B=AC=E5=8F=
=B7=E7=9A=84=E5=AD=97=E8=A1=A5=E4=B8=8A=E4=BA=86=EF=BC=89=EF=BC=8C=E5=85=B6=
=E9=A6=96=E6=B1=89=E5=AD=97=E5=B0=B1=E6=98=AF=E8=AF=A5=E5=8D=95=E5=85=83=E5=
=AF=B9=E5=BA=94=E7=9A=84=E6=B1=89=E5=AD=97=E3=80=82=E8=AF=8D=E5=BA=93=E4=B8=
=AD=E8=AE=B0=E5=BD=95=E4=BA=86=E8=AF=8D=E7=9A=84=E8=AF=8D=E9=95=BF=E3=80=81=
=E9=A2=91=E7=8E=87=E3=80=81=E8=AF=8D=E6=80=A7=E4=BB=A5=E5=8F=8A=E8=AF=8D=E3=
=80=82</P>
<P>=E5=8F=A6=E5=A4=96=E7=89=B9=E5=88=AB=E9=9C=80=E8=A6=81=E6=B3=A8=E6=84=8F=
=E7=9A=84=E6=98=AF<STRONG><FONT=20
color=3D#0000ff>=E5=9C=A8=E4=B8=80=E4=B8=AA=E5=8D=95=E5=85=83=E5=86=85=EF=
=BC=8C=E8=AF=8D=E6=98=AF=E6=8C=89=E7=85=A7CCID=E5=A4=A7=E5=B0=8F=E6=8E=92=
=E5=BA=8F=E7=9A=84</FONT></STRONG>=EF=BC=81=E8=BF=99=E5=AF=B9=E6=88=91=E4=
=BB=AC=E5=90=8E=E9=9D=A2=E7=9A=84=E5=88=86=E6=9E=90=E8=87=B3=E5=85=B3=E9=87=
=8D=E8=A6=81=E3=80=82</P>
<DIV class=3Dcode>
<DIV class=3Dtitle>
<DIV style=3D"FLOAT: right"><IMG class=3DcopyCodeImage=20
src=3D"http://www.cnblogs.com/images/cnblogs_com/zhenyulu/200701/copycode=
.gif"=20
align=3DabsMiddle name=3DccImage> <A onclick=3DCopyCode(this) =
href=3D"javascript:">Copy=20
Code</A></DIV>
<DIV style=3D"CLEAR: =
none">ICTCLAS=E8=AF=8D=E5=BA=93=E9=83=A8=E5=88=86=E5=86=85=E5=AE=B9</DIV>=
</DIV>
<DIV class=3Dcontent>=E6=B1=89=E5=AD=97:=E5=9F=83, ID =EF=BC=9A2 =
<BR><BR> =E8=AF=8D=E9=95=BF =E9=A2=91=E7=8E=87 =
=E8=AF=8D=E6=80=A7 =E8=AF=8D=20
<BR> 0 128 h =
(=E5=9F=83)=20
<BR> 0 0 =20
j (=E5=9F=83) <BR> =
2 =20
4 n (=E5=9F=83)=E9=95=91 =
<BR> =20
2 28 ns (=E5=9F=83)=E9=95=91 =
<BR> =20
4 4 n =
(=E5=9F=83)=E8=8F=B2=E5=B0=94=20
<BR> 2 511 ns =
(=E5=9F=83)=E5=8F=8A=20
<BR> 4 4 =
ns =20
(=E5=9F=83)=E5=85=8B=E6=A3=AE <BR> =
6 2 =20
ns (=E5=9F=83)=E6=8B=89=E7=89=B9=E6=B9=BE <BR> =
4 =20
4 nr (=E5=9F=83)=E9=87=8C=E6=B8=A9 =
<BR> =20
6 2 nz =
(=E5=9F=83)=E9=BB=98=E9=B2=81=E5=B8=82=20
<BR> 2 27 =
n =20
(=E5=9F=83)=E5=A1=9E <BR> 8 =
64 ns =20
(=E5=9F=83)=E5=A1=9E=E4=BF=84=E6=AF=94=E4=BA=9A <BR> =
22 2 ns =20
(=E5=9F=83)=E5=A1=9E=E4=BF=84=E6=AF=94=E4=BA=9A=E8=81=94=E9=82=A6=E6=B0=91=
=E4=B8=BB=E5=85=B1=E5=92=8C=E5=9B=BD <BR> =
4 =20
3 ns (=E5=9F=83)=E5=A1=9E=E8=90=A8 =
<BR> =20
4 4 ns =
(=E5=9F=83)=E8=88=8D=E5=BE=B7=20
<BR> 6 2 =
nr =20
(=E5=9F=83)=E6=96=AF=E7=89=B9=E8=A7=92 <BR> =
4 2 =20
ns (=E5=9F=83)=E6=9D=BE=E7=9C=81 <BR> =
4 =20
3 nr (=E5=9F=83)=E7=89=B9=E7=BA=B3 =
<BR> =20
6 2 nz =
(=E5=9F=83)=E5=9B=A0=E9=9C=8D=E6=B8=A9=20
<BR>=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =
<BR>=E6=B1=89=E5=AD=97:=E6=8C=A8, ID =EF=BC=9A3 <BR><BR> =
=E8=AF=8D=E9=95=BF =20
=E9=A2=91=E7=8E=87 =E8=AF=8D=E6=80=A7 =E8=AF=8D =
<BR> 0 =20
56 h (=E6=8C=A8) <BR> =20
2 1 j =
(=E6=8C=A8)=E6=AC=A1=20
<BR> 2 19 =
n =20
(=E6=8C=A8)=E6=89=93 <BR> 2 =
3 =20
ns (=E6=8C=A8)=E5=86=BB <BR> =
2 =20
1 n (=E6=8C=A8)=E6=96=97 =
<BR> =20
2 9 ns =
(=E6=8C=A8)=E9=A5=BF=20
<BR> 2 4 =
ns =20
(=E6=8C=A8)=E4=B8=AA <BR> 4 =
2 =20
ns (=E6=8C=A8)=E4=B8=AA=E5=84=BF <BR> =
6 17 =20
nr (=E6=8C=A8)=E5=AE=B6=E6=8C=A8=E6=88=B7 <BR> =
2 =20
1 nz (=E6=8C=A8)=E8=BF=91 <BR> =
2 0 n =
(=E6=8C=A8)=E9=AA=82=20
<BR> 6 1 =
ns =20
(=E6=8C=A8)=E9=97=A8=E6=8C=A8=E6=88=B7 <BR> =
2 1 =20
ns (=E6=8C=A8)=E6=89=B9 <BR> =
2 =20
0 ns (=E6=8C=A8)=E6=95=B4 <BR> =
2 =20
12 ns (=E6=8C=A8)=E7=9D=80 =
<BR> =20
2 0 nr =
(=E6=8C=A8)=E6=8F=8D=20
<BR>=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =
<BR>=E6=B1=89=E5=AD=97:=E5=93=8E, ID =EF=BC=9A4 <BR><BR> =
=E8=AF=8D=E9=95=BF =20
=E9=A2=91=E7=8E=87 =E8=AF=8D=E6=80=A7 =E8=AF=8D =
<BR> 0 =20
10 h (=E5=93=8E) <BR> =20
2 3 j =
(=E5=93=8E)=E5=91=80=20
<BR> 2 2 =20
n (=E5=93=8E)=E5=93=9F =
<BR>=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =
<BR>=E6=B1=89=E5=AD=97:=E5=94=89, ID =EF=BC=9A5=20
<BR><BR> =E8=AF=8D=E9=95=BF =E9=A2=91=E7=8E=87 =
=E8=AF=8D=E6=80=A7 =E8=AF=8D <BR> =20
0 9 h (=E5=94=89)=20
<BR> 6 4 =20
j (=E5=94=89)=E5=A3=B0=E5=8F=B9=E6=B0=94</DIV></DIV>
<P>=E5=9C=A8=E8=BF=99=E9=87=8C=E8=BF=98=E5=BA=94=E5=BD=93=E6=B3=A8=E6=84=8F=
=E7=9A=84=E6=98=AF=EF=BC=8C=E4=B8=80=E4=B8=AA=E8=AF=8D=E5=8F=AF=E8=83=BD=E6=
=9C=89=E5=A4=9A=E4=B8=AA=E8=AF=8D=E6=80=A7=EF=BC=8C=E5=9B=A0=E6=AD=A4=E4=B8=
=80=E4=B8=AA=E8=AF=8D=E5=8F=AF=E8=83=BD=E5=9C=A8=E8=AF=8D=E5=85=B8=E4=B8=AD=
=E5=87=BA=E7=8E=B0=E5=A4=9A=E6=AC=A1=EF=BC=8C=E4=BD=86=E8=AF=8D=E6=80=A7=E4=
=B8=8D=E5=90=8C=E3=80=82=E8=8B=A5=E6=83=B3=E4=BB=8E=E8=AF=8D=E5=85=B8=E4=B8=
=AD=E5=94=AF=E4=B8=80=E5=AE=9A=E4=BD=8D=E4=B8=80=E4=B8=AA=E8=AF=8D=E7=9A=84=
=E8=AF=9D=EF=BC=8C=E5=BF=85=E9=A1=BB=E5=90=8C=E6=97=B6=E6=8C=87=E6=98=8E=E8=
=AF=8D=E4=B8=8E=E8=AF=8D=E6=80=A7=E3=80=82</P>
<P>=E5=8F=A6=E5=A4=96=E5=9C=A8WordDictionary=E7=B1=BB=E4=B8=AD=E7=94=A8=E5=
=88=B0=E5=BE=97=E6=AF=94=E8=BE=83=E5=A4=9A=E7=9A=84=E5=B0=B1=E6=98=AF=E8=AF=
=8D=E7=9A=84=E6=A3=80=E7=B4=A2=EF=BC=8C=E8=BF=99=E7=94=B1FindInOriginalTa=
ble=E6=96=B9=E6=B3=95=E5=AE=9E=E7=8E=B0=E3=80=82=E5=8E=9FICTCLAS=E4=BB=A3=
=E7=A0=81=E4=B8=AD=E8=AF=A5=E6=96=B9=E6=B3=95=E7=9A=84=E5=AE=9E=E7=8E=B0=E7=
=BB=93=E6=9E=84=E6=AF=94=E8=BE=83=E5=A4=8D=E6=9D=82=EF=BC=8C=E5=90=8C=E6=97=
=B6=E8=80=83=E8=99=91=E4=BA=86=E5=A4=9A=E7=A7=8D=E6=A3=80=E7=B4=A2=E9=9C=80=
=E6=B1=82=EF=BC=8C=E5=9B=A0=E6=AD=A4=E4=BB=A3=E7=A0=81=E4=B9=9F=E7=9B=B8=E5=
=AF=B9=E5=A4=8D=E6=9D=82=E4=B8=80=E4=BA=9B=E3=80=82=E5=9C=A8SharpICTCLAS=E4=
=B8=AD=EF=BC=8C=E6=88=91=E5=AF=B9=E8=AF=A5=E6=96=B9=E6=B3=95=E8=BF=9B=E8=A1=
=8C=E4=BA=86=E9=87=8D=E8=BD=BD=EF=BC=8C=E9=92=88=E5=AF=B9=E4=B8=8D=E5=90=8C=
=E6=A3=80=E7=B4=A2=E7=9B=AE=E7=9A=84=E8=AE=BE=E8=AE=A1=E4=BA=86=E4=B8=8D=E5=
=90=8C=E7=9A=84FindInOriginalTable=E6=96=B9=E6=B3=95=EF=BC=8C=E7=AE=80=E5=
=8C=96=E4=BA=86=E7=A8=8B=E5=BA=8F=E6=8E=A5=E5=8F=A3=E5=92=8C=E4=BB=A3=E7=A0=
=81=E5=A4=8D=E6=9D=82=E5=BA=A6=E3=80=82=E5=85=B6=E4=B8=AD=E4=B8=80=E4=B8=AA=
FindInOriginalTable=E6=96=B9=E6=B3=95=E4=BB=A3=E7=A0=81=E5=A6=82=E4=B8=8B=
=EF=BC=8C=E5=AE=9E=E7=8E=B0=E4=BA=86=E5=88=A4=E6=96=AD=E6=9F=90=E4=B8=80=E8=
=AF=8D=E6=80=A7=E7=9A=84=E4=B8=80=E8=AF=8D=E6=98=AF=E5=90=A6=E5=AD=98=E5=9C=
=A8=E5=8A=9F=E8=83=BD=E3=80=82</P>
<DIV class=3Dcode>
<DIV class=3Dtitle>
<DIV style=3D"FLOAT: right"><IMG class=3DcopyCodeImage=20
src=3D"http://www.cnblogs.com/images/cnblogs_com/zhenyulu/200701/copycode=
.gif"=20
align=3DabsMiddle name=3DccImage> <A onclick=3DCopyCode(this) =
href=3D"javascript:">Copy=20
Code</A></DIV>
<DIV style=3D"CLEAR: =
none">FindInOriginalTable=E6=96=B9=E6=B3=95=E7=9A=84=E4=B8=80=E4=B8=AA=E9=
=87=8D=E8=BD=BD=E7=89=88=E6=9C=AC</DIV></DIV>
<DIV class=3Dcontent><SPAN style=3D"COLOR: #0000ff">private</SPAN> <SPAN =
style=3D"COLOR: #0000ff">bool</SPAN> FindInOriginalTable(<SPAN=20
style=3D"COLOR: #0000ff">int</SPAN> nInnerCode, <SPAN=20
style=3D"COLOR: #0000ff">string</SPAN> sWord, <SPAN=20
style=3D"COLOR: #0000ff">int</SPAN> nPOS) <BR>{ <BR> =
WordItem[] pItems=20
=3D indexTable[nInnerCode].WordItems; <BR><BR> <SPAN=20
style=3D"COLOR: #0000ff">int</SPAN> nStart =3D 0, nEnd =3D=20
indexTable[nInnerCode].nCount - 1; <BR> <SPAN=20
style=3D"COLOR: #0000ff">int</SPAN> nMid =3D (nStart + nEnd) / 2, =
nCmpValue;=20
<BR><BR> <SPAN style=3D"COLOR: #008000">//Binary search=20
</SPAN><BR> <SPAN style=3D"COLOR: #0000ff">while</SPAN> =
(nStart <=3D=20
nEnd) <BR> { <BR> nCmpValue =
=3D=20
Utility.CCStringCompare(pItems[nMid].sWord, sWord);=20
<BR><BR> <SPAN style=3D"COLOR: =
#0000ff">if</SPAN>=20
(nCmpValue =3D=3D 0 && (pItems[nMid].nPOS =3D=3D nPOS || nPOS =
=3D=3D -1))=20
<BR> <SPAN=20
style=3D"COLOR: #0000ff">return</SPAN> <SPAN=20
style=3D"COLOR: #0000ff">true</SPAN>;<SPAN style=3D"COLOR: =
#008000">//find it=20
</SPAN><BR> <SPAN=20
style=3D"COLOR: #0000ff">else</SPAN> <SPAN style=3D"COLOR: =
#0000ff">if</SPAN>=20
(nCmpValue < 0 || (nCmpValue =3D=3D 0 && pItems[nMid].nPOS =
< nPOS=20
&& nPOS !=3D -1)) =
<BR> =20
nStart =3D nMid + 1; <BR> <SPAN=20
style=3D"COLOR: #0000ff">else</SPAN> <SPAN style=3D"COLOR: =
#0000ff">if</SPAN>=20
(nCmpValue > 0 || (nCmpValue =3D=3D 0 && pItems[nMid].nPOS =
> nPOS=20
&& nPOS !=3D -1)) =
<BR> =20
nEnd =3D nMid - 1; <BR><BR> nMid =3D =
(nStart + nEnd) /=20
2; <BR> } <BR> <SPAN=20
style=3D"COLOR: #0000ff">return</SPAN> <SPAN style=3D"COLOR: =
#0000ff">false</SPAN>;=20
<BR>} <BR></DIV></DIV>
<P>=E5=85=B6=E5=AE=83=E5=8A=9F=E8=83=BD=E5=9C=A8=E8=BF=99=E9=87=8C=E5=B0=B1=
=E4=B8=8D=E5=86=8D=E4=BB=8B=E7=BB=8D=E4=BA=86=E3=80=82</P>
<UL>
<LI><FONT color=3D#800080><STRONG>=E5=B0=8F=E7=BB=93</STRONG></FONT> =
</LI></UL>
<P>1=E3=80=81WordDictionary=E7=B1=BB=E5=AE=9E=E7=8E=B0=E4=BA=86=E5=AF=B9=E5=
=AD=97=E5=85=B8=E7=9A=84=E8=AF=BB=E5=8F=96=E3=80=81=E5=86=99=E5=85=A5=E3=80=
=81=E6=9B=B4=E6=94=B9=E3=80=81=E6=A3=80=E7=B4=A2=E7=AD=89=E5=8A=9F=E8=83=BD=
=E3=80=82</P>
<P>2=E3=80=81=E8=AF=8D=E5=85=B8=E4=B8=AD=E8=AE=B0=E5=BD=95=E4=BA=86=E4=BB=
=A56768=E4=B8=AA=E6=B1=89=E5=AD=97=E6=89=93=E5=A4=B4=E7=9A=84=E8=AF=8D=E3=
=80=81=E8=AF=8D=E6=80=A7=E3=80=81=E5=87=BA=E7=8E=B0=E9=A2=91=E7=8E=87=E7=9A=
=84=E4=BF=A1=E6=81=AF=EF=BC=8C=E5=85=B7=E4=BD=93=E7=BB=93=E6=9E=84=E9=9C=80=
=E8=A6=81=E4=BA=86=E8=A7=A3=E3=80=82</P>
<P>=E3=80=80</P></DIV>
<DIV class=3Dpostfoot>posted on 2007-03-08 14:25 <A=20
href=3D"http://zhenyulu.cnblogs.com/">=E5=90=95=E9=9C=87=E5=AE=87</A> =
=E9=98=85=E8=AF=BB(440) <A=20
href=3D"http://www.cnblogs.com/zhenyulu/articles/668024.html#Post">=E8=AF=
=84=E8=AE=BA(5)</A>=20
<A=20
href=3D"http://www.cnblogs.com/zhenyulu/admin/EditArticles.aspx?postid=3D=
668024">=E7=BC=96=E8=BE=91</A> <A=20
href=3D"http://www.cnblogs.com/zhenyulu/AddToFavorite.aspx?id=3D668024">=E6=
=94=B6=E8=97=8F</A> <A=20
href=3D"http://www.cnblogs.com/zhenyulu/services/trackbacks/668024.aspx">=
=E5=BC=95=E7=94=A8</A> <A=20
href=3D"javascript:d=3Ddocument;t=3Dd.selection?(d.selection.type!=3D'Non=
e'?d.selection.createRange().text:''):(d.getSelection?d.getSelection():''=
);void(saveit=3Dwindow.open('http://wz.csdn.net/storeit.aspx?t=3D'+escape=
(d.title)+'&u=3D'+escape(d.location.href)+'&c=3D'+escape(t),'save=
it','scrollbars=3Dno,width=3D590,height=3D300,left=3D75,top=3D20,status=3D=
no,resizable=3Dyes'));saveit.focus();">=E7=BD=91=E6=91=98</A>=20
=E6=89=80=E5=B1=9E=E5=88=86=E7=B1=BB: <A =
href=3D"http://www.cnb
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -