You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by cu...@apache.org on 2005/09/08 21:45:01 UTC
svn commit: r279605 [2/4] - in /lucene/nutch/branches/mapred: ./ bin/ conf/
docs/ca/ docs/de/ docs/en/ docs/es/ docs/fi/ docs/fr/ docs/hu/ docs/jp/
docs/ms/ docs/nl/ docs/pl/ docs/pt/ docs/sv/ docs/th/ docs/zh/ lib/ site/
src/java/org/apache/nutch/anal...
Modified: lucene/nutch/branches/mapred/site/credits.pdf
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/site/credits.pdf?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/site/credits.pdf (original)
+++ lucene/nutch/branches/mapred/site/credits.pdf Thu Sep 8 12:42:44 2005
@@ -58,10 +58,10 @@
>>
endobj
14 0 obj
-<< /Length 2147 /Filter [ /ASCII85Decode /FlateDecode ]
+<< /Length 2288 /Filter [ /ASCII85Decode /FlateDecode ]
>>
stream
-Gatm=968iG&AII3Ya:;i#Rl4oOM/V)S]5qKC2<[5...@98S0C>(BqD>fuGfeHHXPt_J?br[RSEV<5,OkMAt8Nbtg=GVU*NID3WtQe/OO?WPF$dZCSRa41="?e]<u2Cf$5CO6KPkml_d7P:0UQR'mC][3;1YHM.>,PD*aM,kkB.(4/%3p%0@Ff^7oh,5&*7'uEVT&C/Vh6GUIf_cq/6DG\&97?N7eaq3WLWYU2m\r9R9VcAdOb!uX>8V3Q4HZX9_Bi$PRSq=[/9jb2`!.AHB#7FI4DR0RiT*gV6*Fp-cC?=7A!:*J=e5RhKc+p\]Xp.1T^4^J3"YS#WP=t."RO'pj*L"KbBIS;2kA6b(+56,qdmh/r[tU?ANF/X=E)IH8T6U+(AujZOFn]=2WMCS\g"hGN\V/SDMo1ls/O$#H)ck=>nCeGX"R=@^$XqO';l"WuEifeRkj2`h/qi&4i(T[J]EsIT.8nrF]>eOgMWR[I?JC.3UKV8D=NDffDn\>e3U4Gt'`VCW><KU?.XA-MEHuU3^"QtLV0nGG[S7mBPL3LA@@L&RFnLk_qi-rO0(m!f6QO8HqAn^f^(Z!S99BI3jB[;/"lQB4m0>=#CI=n=jH.fA<a<H`<u2u=#2mua9DH$Ng(LA*31qs+_4p1X%Odf_=.fQNAI47UYNj#&o6A@Ia!M(;-O:`p=YNGb[+W#fX<E6(P)Da]Q]W^@eT.d)Ab\#1Li=rD,bsWL:bJkM*J3+70<\gf[fU[s;pg"$f<SiF==gQUR.soG0)g=^69F;>Q;=!2D;"VCO4Kep_7GEN!(*R4D4\mhY92V=U#)L+]51Ks.70)#B<]@m,0Ef8b]J]n%jgr[4[Y7PTB).l$hk`4cC.N~>
+Gatm=>Bci#&:XAWTJ(Yt%ne1!"S?PpD75qIS2A@PjYVB.[VXE38MQ5arUh0S&7[C1qt/sg.%9W%d#;R+io5E1IcX_^[>B%@S.TNoUDADFC'=a[K^7:?&_;A>rHUm"\(3X\ebIg/Q6]=)aF*U1qTHIb"rM)PVIB0A(q0h'#S2l61S8mR;rUj_Y,;`cVi1I[q00`'&V[K[5=M?KPhQ+6X>%jJf!!Jb7'@L]_d(3$36'&Bh\KMCTC-@lbk*aXp7jLoHp$n7hm3qtHNmNF*f)BL_ED[Ih9CD:?/4m?Y#+\SePa_G^a>?ClN`3or4rt_,5WYPF".cL:dc+M[fCg-%fBX[UXn'TH8!lYSnDa`'o*q)4Up+=IQ1OJ`Uf/RkI]Qq?KU!O^:(@qFoLlRe2ojIeR\-al\P,F*;C]4HJh3[!4?1I^kZa<lD*5!;WQ[WGo+83!I,+P&A8'5VD2n??>bZF8lpf'ie\#MRD%dMe@=Tpc;s+LNF]5N,bEpA%lWE%4'*;U9#aSi'm[-.5A-H6bHp#:4CN1M*1*Oe6(On@_B`kun"O'aUO99ZN_3.''dc4PBBuq`qn6t_:?MFq1p@-lg74j)I[*DY?&WB8:8lF:3(>Q'"Eiu(&0eeh@>(3ncMFsO/?m#7-jd.A!.o/"\F!+)7QU'eBEoFi,j15-SRk%Xn[;O6Y<U7cL%&:X$o0FC"sAk2@uBp8b)Hi$q79(9)dLe\@Ce&oDaOf/AeP;+Q:UM3n8WLlF"iYi9Jk:1NkB[0qc.p^SnCW_eP2QmAe*Eo9@o0N_^XGriki*M>nnQt)*':j.sA+FW@OD)UA7`+q;!D$$(MGtk\^m]L(L`9iOofINi5[7i&?'^>H!G"*TlTQ\8;LYn&]RK`Y;#C9l>hP[4PdoFkJHKGO)OM"J\d]`<<Hc&rHSXjlXoRTL)#?RJWP7NZYS67KVK-2E`NM.goZ>h\C0goCL!bgW\:(kN.pR%DA/s+IG:CG4]f0a;aWL*gr7g%188`a@-g:A\8cbcoQ99[KFo4!!j(LLt`GKgh0<CgeI;Wp\!9XAB!X>F*/Y=2?X/0+T)OdN@C%f0mW]m:h2m(CJZj30/Q>2]IVn5PT1/.,WIDU"Y3r`[(+3=D?He3eDc2J=AB0%[9=V%"je_q]s;V-,Ei2ZTHI+(;G`V#^809@;6``JRCf^rg(7)O"4upqBO\A-7>ftiR>kN`:PIB0B_n>#6Z$U6>t=\HKlhO/n"ERHl\D[kHnDV,5=`h:O\KR:+hn.p&R;MU4Hp5dZH]C>VIh9:JlI^i^VusO1G[20D9YTj_?8u%ZIfE0oObK[;EWlbT2rI8qZ#Z)LECel:_op$][!bAo5M=0icYT:iBf;PK6;6e#^k6_9QIa26$b^_X/H<aJKk;pd79!Yi^64lI0f!#p9kb=+!J!?&q$+DRr+lTB@lO@<l"Vu>HZbqcu2"L0MZUP@g@AP!V_5#L[omkTNf3K*5eJZa@;6D/d[PTNPND1^2Gca)qm6q:H6^uYKc*EPi/:c)j-)Z^joMgWiCrgNo$M\aHVKs:ls1&ksBjf4Ws0V-sA?!gP$2U#cNHo)1ZD+:i2*Nr[QB+$V.q&*^g)84Zu?3hY!^332$_"eG_Q[.\&a\p$gPH7Q2_S;,JUtUbW(D)M*T=oMlbVqC8TgR?Wa@$BbNTqtK=4@_s=(#16Ar=/G.1X6?l7lac&NcO%)6,J%Cj7rEK*N[M5T]KEtj4uG3_Wf,k_?s4pZK-3`m_`3;N(Zr]QV0$"fiZ+nW8RjfgPWdW>%MuP]D0Lj$T]!D.L7F`mIq<U>fRuGXGk^0qqd..^]+:f5-2#>nG9;^uYAY540@sBT8q@g[d"N$J#Zq.NB^(4a5!RPo8FOX]=rU_o3Q#rE#c@jBW&bTJ$&X]k;VZK.`^g8jk"`Tr>DK/P>%D>La9DQ]^=\-"lG:=Os'*LhG^>KPnlfJ=G]O2)ggYqjI$&FBS3TiY7q8*ih**jM@5cS`A*'gc4`Fl/_[O#'L\l5_(Ue`E732l#G6*:2J.Q;cklWUpCI=n=jH.fA<a<H`<u3"3#@PJ'9DH$Ng(LA*31s)O_4p1X%OgXZ;kO-JA-n.TDsD[Lo=3!7V^;[P-O="[fqZK_ct;T5Z%haIOIXR:\VNokWKq<W/&R\dch=m1Q=NC3lcQ'3X@'32oAsi"a/hN@[u0T#>fh_[@BlU8@,#=cbOK4,%S`#BQ;<rFYM&M_*j+!^KCo5B!JF,PDk>*jY92Uc6bPk5GM0:#;hQ4&b$^-_7?jW,1=IOU5EsqBoF*`0Iut,N=h+J3Z8E,K~>
endstream
endobj
15 0 obj
@@ -87,15 +87,16 @@
26 0 R
27 0 R
28 0 R
+29 0 R
]
endobj
17 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 108.0 607.266 173.676 595.266 ]
+/Rect [ 108.0 607.266 184.98 595.266 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://www.nutch.org/blog/cutting.html)
+/A << /URI (http://www.frutch.org/)
/S /URI >>
/H /I
>>
@@ -103,10 +104,10 @@
18 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 152.328 536.532 268.62 524.532 ]
+/Rect [ 108.0 594.066 173.676 582.066 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://research.yahoo.com/)
+/A << /URI (http://www.nutch.org/blog/cutting.html)
/S /URI >>
/H /I
>>
@@ -114,10 +115,10 @@
19 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 108.0 523.332 213.66 511.332 ]
+/Rect [ 152.328 510.132 268.62 498.132 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://www.fenwick.com/)
+/A << /URI (http://research.yahoo.com/)
/S /URI >>
/H /I
>>
@@ -125,10 +126,10 @@
20 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 192.312 510.132 289.968 498.132 ]
+/Rect [ 108.0 496.932 213.66 484.932 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://www.media-style.com/)
+/A << /URI (http://www.fenwick.com/)
/S /URI >>
/H /I
>>
@@ -136,10 +137,10 @@
21 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 182.976 496.932 268.944 484.932 ]
+/Rect [ 192.312 483.732 289.968 471.732 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://www.archive.org/)
+/A << /URI (http://www.media-style.com/)
/S /URI >>
/H /I
>>
@@ -147,7 +148,7 @@
22 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 192.996 483.732 278.964 471.732 ]
+/Rect [ 182.976 470.532 268.944 458.532 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A << /URI (http://www.archive.org/)
@@ -158,10 +159,10 @@
23 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 155.652 470.532 248.316 458.532 ]
+/Rect [ 192.996 457.332 278.964 445.332 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://www.digitalconsumer.org/)
+/A << /URI (http://www.archive.org/)
/S /URI >>
/H /I
>>
@@ -169,10 +170,10 @@
24 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 208.992 444.132 289.632 432.132 ]
+/Rect [ 155.652 444.132 248.316 432.132 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://www.indexventures.com/)
+/A << /URI (http://www.digitalconsumer.org/)
/S /URI >>
/H /I
>>
@@ -180,10 +181,10 @@
25 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 174.012 430.932 206.676 418.932 ]
+/Rect [ 208.992 417.732 289.632 405.732 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://www.groxis.com/)
+/A << /URI (http://www.indexventures.com/)
/S /URI >>
/H /I
>>
@@ -191,10 +192,10 @@
26 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 185.328 417.732 241.98 405.732 ]
+/Rect [ 174.012 404.532 206.676 392.532 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://malachiarts.com/)
+/A << /URI (http://www.groxis.com/)
/S /URI >>
/H /I
>>
@@ -202,10 +203,10 @@
27 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 108.0 373.398 217.296 361.398 ]
+/Rect [ 185.328 391.332 241.98 379.332 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://research.yahoo.com/)
+/A << /URI (http://malachiarts.com/)
/S /URI >>
/H /I
>>
@@ -213,7 +214,18 @@
28 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 108.0 346.998 208.632 334.998 ]
+/Rect [ 108.0 346.998 217.296 334.998 ]
+/C [ 0 0 0 ]
+/Border [ 0 0 0 ]
+/A << /URI (http://research.yahoo.com/)
+/S /URI >>
+/H /I
+>>
+endobj
+29 0 obj
+<< /Type /Annot
+/Subtype /Link
+/Rect [ 108.0 320.598 208.632 308.598 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A << /URI (http://www.archive.org/)
@@ -221,57 +233,57 @@
/H /I
>>
endobj
-30 0 obj
+31 0 obj
<<
/Title (\376\377\0\61\0\40\0\103\0\157\0\155\0\155\0\151\0\164\0\164\0\145\0\162\0\163)
- /Parent 29 0 R
- /Next 31 0 R
+ /Parent 30 0 R
+ /Next 32 0 R
/A 9 0 R
>> endobj
-31 0 obj
+32 0 obj
<<
/Title (\376\377\0\62\0\40\0\106\0\162\0\151\0\145\0\156\0\144\0\163)
- /Parent 29 0 R
- /Prev 30 0 R
- /Next 32 0 R
+ /Parent 30 0 R
+ /Prev 31 0 R
+ /Next 33 0 R
/A 11 0 R
>> endobj
-32 0 obj
+33 0 obj
<<
/Title (\376\377\0\63\0\40\0\123\0\160\0\157\0\156\0\163\0\157\0\162\0\163)
- /Parent 29 0 R
- /Prev 31 0 R
+ /Parent 30 0 R
+ /Prev 32 0 R
/A 13 0 R
>> endobj
-33 0 obj
+34 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F3
/BaseFont /Helvetica-Bold
/Encoding /WinAnsiEncoding >>
endobj
-34 0 obj
+35 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F5
/BaseFont /Times-Roman
/Encoding /WinAnsiEncoding >>
endobj
-35 0 obj
+36 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F1
/BaseFont /Helvetica
/Encoding /WinAnsiEncoding >>
endobj
-36 0 obj
+37 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F2
/BaseFont /Helvetica-Oblique
/Encoding /WinAnsiEncoding >>
endobj
-37 0 obj
+38 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F7
@@ -286,13 +298,13 @@
2 0 obj
<< /Type /Catalog
/Pages 1 0 R
- /Outlines 29 0 R
+ /Outlines 30 0 R
/PageMode /UseOutlines
>>
endobj
3 0 obj
<<
-/Font << /F3 33 0 R /F5 34 0 R /F1 35 0 R /F2 36 0 R /F7 37 0 R >>
+/Font << /F3 34 0 R /F5 35 0 R /F1 36 0 R /F2 37 0 R /F7 38 0 R >>
/ProcSet [ /PDF /ImageC /Text ] >>
endobj
9 0 obj
@@ -304,66 +316,67 @@
11 0 obj
<<
/S /GoTo
-/D [15 0 R /XYZ 85.0 561.866 null]
+/D [15 0 R /XYZ 85.0 535.466 null]
>>
endobj
13 0 obj
<<
/S /GoTo
-/D [15 0 R /XYZ 85.0 398.732 null]
+/D [15 0 R /XYZ 85.0 372.332 null]
>>
endobj
-29 0 obj
+30 0 obj
<<
- /First 30 0 R
- /Last 32 0 R
+ /First 31 0 R
+ /Last 33 0 R
>> endobj
xref
-0 38
+0 39
0000000000 65535 f
-0000006763 00000 n
-0000006828 00000 n
-0000006920 00000 n
+0000007084 00000 n
+0000007149 00000 n
+0000007241 00000 n
0000000015 00000 n
0000000071 00000 n
0000000584 00000 n
0000000704 00000 n
0000000743 00000 n
-0000007043 00000 n
+0000007364 00000 n
0000000878 00000 n
-0000007106 00000 n
+0000007427 00000 n
0000001013 00000 n
-0000007172 00000 n
+0000007493 00000 n
0000001150 00000 n
-0000003390 00000 n
-0000003513 00000 n
-0000003617 00000 n
-0000003807 00000 n
-0000003986 00000 n
-0000004160 00000 n
-0000004341 00000 n
-0000004518 00000 n
-0000004695 00000 n
-0000004880 00000 n
-0000005063 00000 n
-0000005239 00000 n
-0000005415 00000 n
-0000005593 00000 n
-0000007238 00000 n
-0000005768 00000 n
-0000005919 00000 n
-0000006067 00000 n
-0000006207 00000 n
-0000006320 00000 n
-0000006430 00000 n
-0000006538 00000 n
-0000006654 00000 n
+0000003531 00000 n
+0000003654 00000 n
+0000003765 00000 n
+0000003938 00000 n
+0000004128 00000 n
+0000004307 00000 n
+0000004481 00000 n
+0000004662 00000 n
+0000004839 00000 n
+0000005016 00000 n
+0000005201 00000 n
+0000005384 00000 n
+0000005560 00000 n
+0000005736 00000 n
+0000005914 00000 n
+0000007559 00000 n
+0000006089 00000 n
+0000006240 00000 n
+0000006388 00000 n
+0000006528 00000 n
+0000006641 00000 n
+0000006751 00000 n
+0000006859 00000 n
+0000006975 00000 n
trailer
<<
-/Size 38
+/Size 39
/Root 2 0 R
/Info 4 0 R
>>
startxref
-7289
+7610
%%EOF
Modified: lucene/nutch/branches/mapred/site/i18n.html
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/site/i18n.html?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/site/i18n.html (original)
+++ lucene/nutch/branches/mapred/site/i18n.html Thu Sep 8 12:42:44 2005
@@ -249,7 +249,7 @@
</ol>
<p>If you'd like to provide a translation, simply post translations of
-these five files to <a href="mailto:dev@nutch.org">dev@nutch.org</a>
+these five files to <a href="mailto:nutch-dev@lucene.apache.org">nutch-dev@lucene.apache.org</a>
as an attachment.</p>
</div>
@@ -347,7 +347,7 @@
<h2 class="h3">Generating Static Pages</h2>
<div class="section">
<p>To generate the static pages you must have <a href="http://java.sun.com/j2se/downloads.html">Java</a>, <a href="http://ant.apache.org/">Ant</a> and Nutch installed. To
- install Nutch, either download and unpack the latest <a href="http://www.nutch.org/release/nightly/">release</a>, or check it
+ install Nutch, either download and unpack the latest <a href="http://lucene.apache.org/nutch/release/nightly/">release</a>, or check it
out from <a href="version_control.html">Subversion</a>.</p>
<p>Then give the command:</p>
<pre>
@@ -365,7 +365,7 @@
<div class="section">
<p>To test the dynamic pages you must also have <a href="http://jakarta.apache.org/tomcat/">Tomcat</a> installed.</p>
<p>An index is also required. You can collect your own by working
-through the <a href="http://www.nutch.org/tutorial.html">tutorial</a>.
+through the <a href="http://lucene.apache.org/nutch/tutorial.html">tutorial</a>.
Once you have an index, follow the steps outlined at the end of the
tutorial for searching.</p>
<i>This documentation needs more detail. Could someone
Modified: lucene/nutch/branches/mapred/site/i18n.pdf
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/site/i18n.pdf?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/site/i18n.pdf (original)
+++ lucene/nutch/branches/mapred/site/i18n.pdf Thu Sep 8 12:42:44 2005
@@ -91,10 +91,10 @@
>>
endobj
20 0 obj
-<< /Length 1680 /Filter [ /ASCII85Decode /FlateDecode ]
+<< /Length 1691 /Filter [ /ASCII85Decode /FlateDecode ]
>>
stream
-Gau0Dhf%7-&:Vr4+lm2@OAJ.jfgRW3/X!M12f+9l$7s(;9=1g%(-ROqir/O3=e^2+.GK7fndn_DO5GA0pDp5WZRbd43ds=VB=>>@SE6%)GjslX;\,J=1a'%>3O?-bkKRh^DOpZT[P)NICLjm%_j[D'O#Q<de...@Ug-R>.uLJ$o1j-;@O4A1D*tAMgQ\6%;4Q`$4&*28^>[&1f')B>ocq@E.qKm@nH'p<\a0fQ?K8h@ZQ%6nd,EG5B.c\$`%)kkV(kRJXk`mQTsl[_]KN-002S52VrcR=JVmMi4m3*a<'E&JH\?DU!l#@gGg?1qEZ89TQ8?/_Y=OB"R%hO:amc#>$QK)<k=<,u!?$i$3n\De^6VP%SLN>V;=[eK0J#YP"cjq<ulNZ4VK%KIg5RnAb)Ce2?_-8^`VX59Q@CMf6gGWj'=J^^VbV/n6k5Tr(d*lV34_0#ntSX[+!=e.Sh\U=^BZOpsguij>nI05'%3p='Zs&UAq'-V.`G.7(u*XHI4m1kZJP]Kf,AZLPPhJfd[3)3N<#VM$F)5'7.>CR;/mr6ND2'7LXXcjKde_D[dl4XR0/H7)s?cuqKtD>>)E*d:(2f=n6Cpr=a8%]<?gTQ#;?dBUZLk9EZFW50BGJ-N+(OgD5R79N7sp>p+_%&O%3r>rl2cJ1SDFRs!X->B=Ak%u9p)N>%HkbU@cqjk'!F3i=7+!d'RMD=]6e_3G;m5>-h+kDrC4[t>)_sH"$_tsTM.UJOj6"ti%;%Cb2^4[+bWAqDOioAdBl#FQC0p&-b8*Xd4Xs!;V6qoT.V6;>hmc`cjFA<_!@g4$T-!](6(C8s<2/R=X84]i;(m[4`:m%AM@=K2ZBfscj*cuig/n1\-^ZUjbO[#2%53-=S1k'+X&F5:YU",i"epQha.o-F5:f0U:hr0)n6B.$6AW9m$H1Nb"$=3Q[bG6^*53/?>>g.KE[*;BXi$C<9Zc\T8@Nq'A'#@E[J&/Grm<jpdqodIOR=P?N)>KE#HK8j/a+M?031`j0VrfA#_'L(lESs#fjf(N5$qn\Jc[p5[`)uO(VYf_5,n01kb,%70l=PK`>XR>fi$`(a*.,Q<8UQTol=+)pPH&!\0Y@0os7NK=_b3NeSS2s!C[V[`3K'q&Y27F)NMX<^9p<A\_S<<6Y"G]mr;]4V]%*HS5m#XbrQ3B`'^CrE'CTlmIEsi6;(PdHgNj@.O">W!eYBjXG(ZDG+Ot0'`#&!@:XAIN,B"]TLOANVQ),PgpTDm\Ea<Ka:,Htj!O\0_OT~>
+Gau0Dhf%7-&:Vr4+lm2@OAN\<]-...@L>9s/'F_?(-^fOY?]:sf!N[tA`+m/0sf#gcuB5SL*_GH.fP$r#L.[W9)Hf\kF#`Zc8+l:A+dpPLCOQIV_G2HQ)EaLU;<*79g!C,YAu+S42XrO_R&0*1,0P,^?IgJ@1#A7[<-+YR(A^C)jaIs0f[>.(l"\;E)PR<^:L0XrhShg4Nsu-fmeqG_!k6b`_Nnmn$P([_48Kp+'7oCf#H-EXeogj9]9@2.p"%IZ$q3to=Ebn<^@(Z./a1nO(5-?fU6u>.J5j]lpS*`8Zh;=Ljc)Po4#DuRqfG-GsC'Job1]RQTdRE-]bok!$:^Ahc?%hYs5iiCWLY'ANA/Rr<Is,pW<~>
endstream
endobj
21 0 obj
@@ -277,43 +277,43 @@
xref
0 38
0000000000 65535 f
-0000008641 00000 n
-0000008720 00000 n
-0000008812 00000 n
+0000008652 00000 n
+0000008731 00000 n
+0000008823 00000 n
0000000015 00000 n
0000000071 00000 n
0000000703 00000 n
0000000823 00000 n
0000000883 00000 n
-0000008935 00000 n
+0000008946 00000 n
0000001018 00000 n
-0000008998 00000 n
+0000009009 00000 n
0000001155 00000 n
-0000009064 00000 n
+0000009075 00000 n
0000001292 00000 n
-0000009130 00000 n
+0000009141 00000 n
0000001429 00000 n
-0000009194 00000 n
+0000009205 00000 n
0000001566 00000 n
-0000009260 00000 n
+0000009271 00000 n
0000001703 00000 n
-0000003476 00000 n
-0000003584 00000 n
-0000005638 00000 n
-0000005746 00000 n
-0000006726 00000 n
-0000009324 00000 n
-0000006834 00000 n
-0000007014 00000 n
-0000007185 00000 n
-0000007403 00000 n
-0000007627 00000 n
-0000007869 00000 n
-0000008085 00000 n
-0000008198 00000 n
-0000008308 00000 n
-0000008416 00000 n
-0000008532 00000 n
+0000003487 00000 n
+0000003595 00000 n
+0000005649 00000 n
+0000005757 00000 n
+0000006737 00000 n
+0000009335 00000 n
+0000006845 00000 n
+0000007025 00000 n
+0000007196 00000 n
+0000007414 00000 n
+0000007638 00000 n
+0000007880 00000 n
+0000008096 00000 n
+0000008209 00000 n
+0000008319 00000 n
+0000008427 00000 n
+0000008543 00000 n
trailer
<<
/Size 38
@@ -321,5 +321,5 @@
/Info 4 0 R
>>
startxref
-9375
+9386
%%EOF
Modified: lucene/nutch/branches/mapred/site/index.html
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/site/index.html?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/site/index.html (original)
+++ lucene/nutch/branches/mapred/site/index.html Thu Sep 8 12:42:44 2005
@@ -184,6 +184,9 @@
<a href="#News">News</a>
<ul class="minitoc">
<li>
+<a href="#17+August+2005%3A+Nutch+0.7+Released">17 August 2005: Nutch 0.7 Released</a>
+</li>
+<li>
<a href="#June+2005%3A+Nutch+graduates+from+Incubator">June 2005: Nutch graduates from Incubator</a>
</li>
<li>
@@ -204,11 +207,17 @@
<a name="N1000C"></a><a name="News"></a>
<h2 class="h3">News</h2>
<div class="section">
-<a name="N10012"></a><a name="June+2005%3A+Nutch+graduates+from+Incubator"></a>
+<a name="N10012"></a><a name="17+August+2005%3A+Nutch+0.7+Released"></a>
+<h3 class="h4">17 August 2005: Nutch 0.7 Released</h3>
+<p>This is the first Nutch release as an Apache Lucene sub-project. See
+ <a href="http://svn.apache.org/viewcvs.cgi/lucene/nutch/trunk/CHANGES.txt?rev=233150">
+ CHANGES.txt</a> for details. The release is available
+ <a href="http://lucene.apache.org/nutch/release/">here</a>.</p>
+<a name="N10024"></a><a name="June+2005%3A+Nutch+graduates+from+Incubator"></a>
<h3 class="h4">June 2005: Nutch graduates from Incubator</h3>
<p>Nutch has now graduated from the Apache incubator, and is now
a Subproject of Lucene.</p>
-<a name="N1001C"></a><a name="January+2005%3A+Nutch+Joins+Apache+Incubator"></a>
+<a name="N1002E"></a><a name="January+2005%3A+Nutch+Joins+Apache+Incubator"></a>
<h3 class="h4">January 2005: Nutch Joins Apache Incubator</h3>
<p>Nutch is a two-year-old open source project, previously
hosted at Sourceforge and backed by its own non-profit
@@ -219,7 +228,7 @@
overhead of an independent non-profit organization. Nutch's
board of directors and its developers were both polled and
supported the move to the Apache foundation.</p>
-<a name="N10026"></a><a name="September+2004%3A+Creative+Commons+launches+Nutch-based+Search"></a>
+<a name="N10038"></a><a name="September+2004%3A+Creative+Commons+launches+Nutch-based+Search"></a>
<h3 class="h4">September 2004: Creative Commons launches Nutch-based Search</h3>
<p>Creative Commons unveiled a beta version of its search
engine, which scours the web for text, images, audio, and video
@@ -227,7 +236,7 @@
no other company or organization.</p>
<p>See the <a href="http://creativecommons.org/press-releases/entry/5064">Creative
Commons Press Release</a> for more details.</p>
-<a name="N10037"></a><a name="September+2004%3A+Oregon+State+University+switches+to+Nutch"></a>
+<a name="N10049"></a><a name="September+2004%3A+Oregon+State+University+switches+to+Nutch"></a>
<h3 class="h4">September 2004: Oregon State University switches to Nutch</h3>
<p>Oregon State University is converting its searching
infrastructure from Googletm to the open source project
Modified: lucene/nutch/branches/mapred/site/index.pdf
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/site/index.pdf?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/site/index.pdf (original)
+++ lucene/nutch/branches/mapred/site/index.pdf Thu Sep 8 12:42:44 2005
@@ -5,10 +5,10 @@
/Producer (FOP 0.20.5) >>
endobj
5 0 obj
-<< /Length 631 /Filter [ /ASCII85Decode /FlateDecode ]
+<< /Length 677 /Filter [ /ASCII85Decode /FlateDecode ]
>>
stream
-Gaua<c#9(*(rl%B(#CN*eFNq-A%+=!V<-'<$I]L>%Lt3"'%iU,NV_PYL)-6u8h+Zr3P]-25M#GDIWJRYn*_\J0gq\5,33WQKYSbJ!8/Fu\Jn1N"DO$MU'3b^haLJD<nr40P%OFLasd;fd$sV$mKWRj`Pu)Z!'a]6r)h)aVTJ%'n6Ii[1&#FZ.fWa'BnS>!jMq6iF$GV>1Lq?Bl0*o?C3!079Fn0G`7`iTX24gcg$"aoGf=&Z?4H=Q1J/g9#nC=%:+0YZqFrUFmK=^,_9:e)H?mkbhfC#'5?)@IHM(F,rJhhnrt\:@:%Jt:<?s8NBHfa.8He]*/pjanY(a,X[1#<J4RqtjrYZ&YN(J1ULcA1<2M%NZ+N!uW3#U-3KV"ln!u,N&\>^R&\80X'.cf"H?<SK-"i&e4n&4&nD?\XPl67H7-)GP$D`^fOjc>c"#PH:9^M%U`1.Yj?WUTJJZtshcRp\$pkM".*N#cuJ\)+>fgg#djJUArAha?QJ3\3`L9Pq4H%0Qt>>(A+!)Vqra:F:/hAgE@=d-rc"0M`P,/XpB&CNXsOp#0S3TDqJ"p<"BlYDQiZkMQlkW4/c^B<HlLHe$<Qh,?q_?s;$(0s'17>'*(qMEUUZrrB^WGjk~>
+Gaua<cYo:,'Z]\?(#CN*e?obJa)5b$9$<pW(9/D+*?8NZ,d9(7)YLk;%4sIuPXJ\43.tr$qc_lQSp>O*E-!*&&jZZk1-kQ2#S<p9%$8"SaR!(M+W/3Ja;aVanWVRYD"naT-:qrY0!o`H&"P=rT<>tJOKXUb!q<8_7#rZ/i\2GGEjhro2/6JMAEfZn.5VjP*VChrBW?h"Z%<\--lMZ]T1r(dqf4puJKKl!^Dm+NQa(F!%p&lLjB^d]3"85GhMf?rXcj=EBn#&4hf`#OC)7P:k[t_*J#`qhoLaW&R^8;u5CfK]"K-JEEY]*X+W>'VGoC#gWY>;8s-7'JNbR@]V,GFT7:/L2D4$XS?U:sF@<Ohk.#VLpOpG\lq"ZEe3i66/Ks?efiISL%Y[YX;%#&O)P$S.*I$`h)6o5Fkb?sjnk08X]$&ZekYuI7XrNg-\.@Wg'4DNFR"/J*=GJ+m>bhM-G1M*Q21,:.IG_,l3\M#2'oDZH$H2lb9YGCYmBQGY.pa?OieaBis9^Qi'V`]_01$PeJ3lTZZF:.)%*rP9c=?g^X8ml,@om7fP-r:nJ_=um5c9F(Y6SKfX7(r,G.>:nu6"\c^;H_/[MqV5omAA_RU"Dg-\@<sEH)&e.NZh`P;BM=t<pjNH[\fsuJ6lAa]:e&nojZcuousnl=oSlb0!>!~>
endstream
endobj
6 0 obj
@@ -27,6 +27,7 @@
12 0 R
14 0 R
16 0 R
+18 0 R
]
endobj
8 0 obj
@@ -42,7 +43,7 @@
10 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 108.0 541.466 332.456 529.466 ]
+/Rect [ 108.0 541.466 300.152 529.466 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A 11 0 R
@@ -52,7 +53,7 @@
12 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 108.0 523.266 339.788 511.266 ]
+/Rect [ 108.0 523.266 332.456 511.266 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A 13 0 R
@@ -62,7 +63,7 @@
14 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 108.0 505.066 445.448 493.066 ]
+/Rect [ 108.0 505.066 339.788 493.066 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A 15 0 R
@@ -72,7 +73,7 @@
16 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 108.0 486.866 413.804 474.866 ]
+/Rect [ 108.0 486.866 445.448 474.866 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A 17 0 R
@@ -80,31 +81,65 @@
>>
endobj
18 0 obj
-<< /Length 1918 /Filter [ /ASCII85Decode /FlateDecode ]
+<< /Type /Annot
+/Subtype /Link
+/Rect [ 108.0 468.666 413.804 456.666 ]
+/C [ 0 0 0 ]
+/Border [ 0 0 0 ]
+/A 19 0 R
+/H /I
+>>
+endobj
+20 0 obj
+<< /Length 2217 /Filter [ /ASCII85Decode /FlateDecode ]
>>
stream
-Gat=,>I2d:&:Vs/E1_XuU=f%-\&**O1/+Ae$kK2`;&n8/CJ..&iuWYt2g-1ED`MNeQQsJ]qsCjonTq[u4SXZm&C]:N/(7$iQ=7Wpb6UhPo,O6%[V+rIj7h^PH"!eRHbP"//$JURit#Yo^/\RM$AQD5-,(IC_H?_a-$Xp6VWkf]\uRSIp;]S+6cD[#ql<i@...@gV2ndHjWPE11>2mrAJVKdS/d[I6UR$QtMh_gqDX9lj[-uQu*l^J,p@b`gm'#G:j@M.<1gRhT"$r[SjCo)\]l8pWXaF`I\4kBtt$bood0)mBLlhX(V$Y_Ln[m+/%H@+itQ0iiIj0E8(h)sV.k#JL"hX.#AXjNPPY"nm[HK+o-ZuT.8~>
+Gat=,>I2d:&:Vs/E1_XuNag1UAi^r?J<jV...@d>?9,hgPI+i2bdW)gH/;]!HYDr9iX.t'b3&%\DuISD^UG/IE-M(h9BuX^+ace:$P(1XF?W!V>`!2fq,8@R<&:LP"t;VA&BPq-Ms*#XIshLr5(8RQrQ9F6!r.,hc97H1o*!3eRk76nQj&3?qn/8(lB8PmJ?[e2$%nqMhF8O/e@2iKDgoY#af)Mbuu#FV7tt6N[tIMcuY0H^1\V=gIIZ<f2q6@82JcqIas\THI6(Llh*`eH-$cSH&]"qSQK11lU?N0d@+jRc?rE6ir0,&74q%~>
endstream
endobj
-19 0 obj
+21 0 obj
<< /Type /Page
/Parent 1 0 R
/MediaBox [ 0 0 612 792 ]
/Resources 3 0 R
-/Contents 18 0 R
-/Annots 20 0 R
+/Contents 20 0 R
+/Annots 22 0 R
>>
endobj
-20 0 obj
+22 0 obj
[
-21 0 R
-22 0 R
+23 0 R
+24 0 R
+25 0 R
+26 0 R
]
endobj
-21 0 obj
+23 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 127.992 383.507 289.644 371.507 ]
+/Rect [ 419.58 599.613 491.916 587.613 ]
+/C [ 0 0 0 ]
+/Border [ 0 0 0 ]
+/A << /URI (http://svn.apache.org/viewcvs.cgi/lucene/nutch/trunk/CHANGES.txt?rev=233150)
+/S /URI >>
+/H /I
+>>
+endobj
+24 0 obj
+<< /Type /Annot
+/Subtype /Link
+/Rect [ 242.628 573.213 263.28 561.213 ]
+/C [ 0 0 0 ]
+/Border [ 0 0 0 ]
+/A << /URI (http://lucene.apache.org/nutch/release/)
+/S /URI >>
+/H /I
+>>
+endobj
+25 0 obj
+<< /Type /Annot
+/Subtype /Link
+/Rect [ 127.992 305.854 289.644 293.854 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A << /URI (http://creativecommons.org/press-releases/entry/5064)
@@ -112,10 +147,10 @@
/H /I
>>
endobj
-22 0 obj
+26 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 329.46 258.254 413.436 246.254 ]
+/Rect [ 329.46 180.601 413.436 168.601 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A << /URI (http://osuosl.org/news_folder/nutch)
@@ -123,74 +158,82 @@
/H /I
>>
endobj
-24 0 obj
+28 0 obj
<<
/Title (\376\377\0\61\0\40\0\116\0\145\0\167\0\163)
- /Parent 23 0 R
- /First 25 0 R
- /Last 28 0 R
- /Count -4
+ /Parent 27 0 R
+ /First 29 0 R
+ /Last 33 0 R
+ /Count -5
/A 9 0 R
>> endobj
-25 0 obj
+29 0 obj
<<
- /Title (\376\377\0\61\0\56\0\61\0\40\0\112\0\165\0\156\0\145\0\40\0\62\0\60\0\60\0\65\0\72\0\40\0\116\0\165\0\164\0\143\0\150\0\40\0\147\0\162\0\141\0\144\0\165\0\141\0\164\0\145\0\163\0\40\0\146\0\162\0\157\0\155\0\40\0\111\0\156\0\143\0\165\0\142\0\141\0\164\0\157\0\162)
- /Parent 24 0 R
- /Next 26 0 R
+ /Title (\376\377\0\61\0\56\0\61\0\40\0\61\0\67\0\40\0\101\0\165\0\147\0\165\0\163\0\164\0\40\0\62\0\60\0\60\0\65\0\72\0\40\0\116\0\165\0\164\0\143\0\150\0\40\0\60\0\56\0\67\0\40\0\122\0\145\0\154\0\145\0\141\0\163\0\145\0\144)
+ /Parent 28 0 R
+ /Next 30 0 R
/A 11 0 R
>> endobj
-26 0 obj
+30 0 obj
<<
- /Title (\376\377\0\61\0\56\0\62\0\40\0\112\0\141\0\156\0\165\0\141\0\162\0\171\0\40\0\62\0\60\0\60\0\65\0\72\0\40\0\116\0\165\0\164\0\143\0\150\0\40\0\112\0\157\0\151\0\156\0\163\0\40\0\101\0\160\0\141\0\143\0\150\0\145\0\40\0\111\0\156\0\143\0\165\0\142\0\141\0\164\0\157\0\162)
- /Parent 24 0 R
- /Prev 25 0 R
- /Next 27 0 R
+ /Title (\376\377\0\61\0\56\0\62\0\40\0\112\0\165\0\156\0\145\0\40\0\62\0\60\0\60\0\65\0\72\0\40\0\116\0\165\0\164\0\143\0\150\0\40\0\147\0\162\0\141\0\144\0\165\0\141\0\164\0\145\0\163\0\40\0\146\0\162\0\157\0\155\0\40\0\111\0\156\0\143\0\165\0\142\0\141\0\164\0\157\0\162)
+ /Parent 28 0 R
+ /Prev 29 0 R
+ /Next 31 0 R
/A 13 0 R
>> endobj
-27 0 obj
+31 0 obj
<<
- /Title (\376\377\0\61\0\56\0\63\0\40\0\123\0\145\0\160\0\164\0\145\0\155\0\142\0\145\0\162\0\40\0\62\0\60\0\60\0\64\0\72\0\40\0\103\0\162\0\145\0\141\0\164\0\151\0\166\0\145\0\40\0\103\0\157\0\155\0\155\0\157\0\156\0\163\0\40\0\154\0\141\0\165\0\156\0\143\0\150\0\145\0\163\0\40\0\116\0\165\0\164\0\143\0\150\0\55\0\142\0\141\0\163\0\145\0\144\0\40\0\123\0\145\0\141\0\162\0\143\0\150)
- /Parent 24 0 R
- /Prev 26 0 R
- /Next 28 0 R
+ /Title (\376\377\0\61\0\56\0\63\0\40\0\112\0\141\0\156\0\165\0\141\0\162\0\171\0\40\0\62\0\60\0\60\0\65\0\72\0\40\0\116\0\165\0\164\0\143\0\150\0\40\0\112\0\157\0\151\0\156\0\163\0\40\0\101\0\160\0\141\0\143\0\150\0\145\0\40\0\111\0\156\0\143\0\165\0\142\0\141\0\164\0\157\0\162)
+ /Parent 28 0 R
+ /Prev 30 0 R
+ /Next 32 0 R
/A 15 0 R
>> endobj
-28 0 obj
+32 0 obj
<<
- /Title (\376\377\0\61\0\56\0\64\0\40\0\123\0\145\0\160\0\164\0\145\0\155\0\142\0\145\0\162\0\40\0\62\0\60\0\60\0\64\0\72\0\40\0\117\0\162\0\145\0\147\0\157\0\156\0\40\0\123\0\164\0\141\0\164\0\145\0\40\0\125\0\156\0\151\0\166\0\145\0\162\0\163\0\151\0\164\0\171\0\40\0\163\0\167\0\151\0\164\0\143\0\150\0\145\0\163\0\40\0\164\0\157\0\40\0\116\0\165\0\164\0\143\0\150)
- /Parent 24 0 R
- /Prev 27 0 R
+ /Title (\376\377\0\61\0\56\0\64\0\40\0\123\0\145\0\160\0\164\0\145\0\155\0\142\0\145\0\162\0\40\0\62\0\60\0\60\0\64\0\72\0\40\0\103\0\162\0\145\0\141\0\164\0\151\0\166\0\145\0\40\0\103\0\157\0\155\0\155\0\157\0\156\0\163\0\40\0\154\0\141\0\165\0\156\0\143\0\150\0\145\0\163\0\40\0\116\0\165\0\164\0\143\0\150\0\55\0\142\0\141\0\163\0\145\0\144\0\40\0\123\0\145\0\141\0\162\0\143\0\150)
+ /Parent 28 0 R
+ /Prev 31 0 R
+ /Next 33 0 R
/A 17 0 R
>> endobj
-29 0 obj
+33 0 obj
+<<
+ /Title (\376\377\0\61\0\56\0\65\0\40\0\123\0\145\0\160\0\164\0\145\0\155\0\142\0\145\0\162\0\40\0\62\0\60\0\60\0\64\0\72\0\40\0\117\0\162\0\145\0\147\0\157\0\156\0\40\0\123\0\164\0\141\0\164\0\145\0\40\0\125\0\156\0\151\0\166\0\145\0\162\0\163\0\151\0\164\0\171\0\40\0\163\0\167\0\151\0\164\0\143\0\150\0\145\0\163\0\40\0\164\0\157\0\40\0\116\0\165\0\164\0\143\0\150)
+ /Parent 28 0 R
+ /Prev 32 0 R
+ /A 19 0 R
+>> endobj
+34 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F3
/BaseFont /Helvetica-Bold
/Encoding /WinAnsiEncoding >>
endobj
-30 0 obj
+35 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F5
/BaseFont /Times-Roman
/Encoding /WinAnsiEncoding >>
endobj
-31 0 obj
+36 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F1
/BaseFont /Helvetica
/Encoding /WinAnsiEncoding >>
endobj
-32 0 obj
+37 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F2
/BaseFont /Helvetica-Oblique
/Encoding /WinAnsiEncoding >>
endobj
-33 0 obj
+38 0 obj
<< /Type /Font
/Subtype /Type1
/Name /F7
@@ -200,97 +243,108 @@
1 0 obj
<< /Type /Pages
/Count 2
-/Kids [6 0 R 19 0 R ] >>
+/Kids [6 0 R 21 0 R ] >>
endobj
2 0 obj
<< /Type /Catalog
/Pages 1 0 R
- /Outlines 23 0 R
+ /Outlines 27 0 R
/PageMode /UseOutlines
>>
endobj
3 0 obj
<<
-/Font << /F3 29 0 R /F5 30 0 R /F1 31 0 R /F2 32 0 R /F7 33 0 R >>
+/Font << /F3 34 0 R /F5 35 0 R /F1 36 0 R /F2 37 0 R /F7 38 0 R >>
/ProcSet [ /PDF /ImageC /Text ] >>
endobj
9 0 obj
<<
/S /GoTo
-/D [19 0 R /XYZ 85.0 659.0 null]
+/D [21 0 R /XYZ 85.0 659.0 null]
>>
endobj
11 0 obj
<<
/S /GoTo
-/D [19 0 R /XYZ 85.0 627.866 null]
+/D [21 0 R /XYZ 85.0 627.866 null]
>>
endobj
13 0 obj
<<
/S /GoTo
-/D [19 0 R /XYZ 85.0 576.613 null]
+/D [21 0 R /XYZ 85.0 550.213 null]
>>
endobj
15 0 obj
<<
/S /GoTo
-/D [19 0 R /XYZ 85.0 459.36 null]
+/D [21 0 R /XYZ 85.0 498.96 null]
>>
endobj
17 0 obj
<<
/S /GoTo
-/D [19 0 R /XYZ 85.0 347.307 null]
+/D [21 0 R /XYZ 85.0 381.707 null]
>>
endobj
-23 0 obj
+19 0 obj
<<
- /First 24 0 R
- /Last 24 0 R
+/S /GoTo
+/D [21 0 R /XYZ 85.0 269.654 null]
+>>
+endobj
+27 0 obj
+<<
+ /First 28 0 R
+ /Last 28 0 R
>> endobj
xref
-0 34
+0 39
0000000000 65535 f
-0000006500 00000 n
-0000006565 00000 n
-0000006657 00000 n
+0000007728 00000 n
+0000007793 00000 n
+0000007885 00000 n
0000000015 00000 n
0000000071 00000 n
-0000000793 00000 n
-0000000913 00000 n
-0000000966 00000 n
-0000006780 00000 n
-0000001101 00000 n
-0000006843 00000 n
-0000001238 00000 n
-0000006909 00000 n
-0000001375 00000 n
-0000006975 00000 n
-0000001512 00000 n
-0000007040 00000 n
-0000001649 00000 n
-0000003660 00000 n
-0000003783 00000 n
-0000003817 00000 n
-0000004023 00000 n
-0000007106 00000 n
-0000004211 00000 n
-0000004352 00000 n
-0000004690 00000 n
-0000005048 00000 n
-0000005512 00000 n
-0000005944 00000 n
-0000006057 00000 n
-0000006167 00000 n
-0000006275 00000 n
-0000006391 00000 n
+0000000839 00000 n
+0000000959 00000 n
+0000001019 00000 n
+0000008008 00000 n
+0000001154 00000 n
+0000008071 00000 n
+0000001291 00000 n
+0000008137 00000 n
+0000001428 00000 n
+0000008203 00000 n
+0000001565 00000 n
+0000008268 00000 n
+0000001702 00000 n
+0000008334 00000 n
+0000001839 00000 n
+0000004149 00000 n
+0000004272 00000 n
+0000004320 00000 n
+0000004548 00000 n
+0000004740 00000 n
+0000004946 00000 n
+0000008400 00000 n
+0000005134 00000 n
+0000005275 00000 n
+0000005566 00000 n
+0000005918 00000 n
+0000006276 00000 n
+0000006740 00000 n
+0000007172 00000 n
+0000007285 00000 n
+0000007395 00000 n
+0000007503 00000 n
+0000007619 00000 n
trailer
<<
-/Size 34
+/Size 39
/Root 2 0 R
/Info 4 0 R
>>
startxref
-7157
+8451
%%EOF
Modified: lucene/nutch/branches/mapred/site/tutorial.html
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/site/tutorial.html?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/site/tutorial.html (original)
+++ lucene/nutch/branches/mapred/site/tutorial.html Thu Sep 8 12:42:44 2005
@@ -246,7 +246,7 @@
<h2 class="h3">Getting Started</h2>
<div class="section">
<p>First, you need to get a copy of the Nutch code. You can download
-a release from <a href="http://www.nutch.org/release/">http://www.nutch.org/release/</a>.
+a release from <a href="http://lucene.apache.org/nutch/release/">http://lucene.apache.org/nutch/release/</a>.
Unpack the release and connect to its top-level directory. Or, check
out the latest source code from <a href="version_control.html">subversion</a> and build it
with <a href="http://ant.apache.org/">Ant</a>.</p>
@@ -277,12 +277,12 @@
<li>Create a flat file of root urls. For example, to crawl the
-<span class="codefrag">nutch.org</span> site you might start with a file named
+<span class="codefrag">nutch</span> site you might start with a file named
<span class="codefrag">urls</span> containing just the Nutch home page. All other
Nutch pages should be reachable from this page. The <span class="codefrag">urls</span>
file would thus look like:
<pre class="code">
-http://www.nutch.org/
+http://lucene.apache.org/nutch/
</pre>
</li>
@@ -291,11 +291,11 @@
<li>Edit the file <span class="codefrag">conf/crawl-urlfilter.txt</span> and replace
<span class="codefrag">MY.DOMAIN.NAME</span> with the name of the domain you wish to
crawl. For example, if you wished to limit the crawl to the
-<span class="codefrag">nutch.org</span> domain, the line should read:
+<span class="codefrag">apache.org</span> domain, the line should read:
<pre class="code">
-+^http://([a-z0-9]*\.)*nutch.org/
++^http://([a-z0-9]*\.)*apache.org/
</pre>
-This will include any url in the domain <span class="codefrag">nutch.org</span>.
+This will include any url in the domain <span class="codefrag">apache.org</span>.
</li>
Modified: lucene/nutch/branches/mapred/site/tutorial.pdf
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/site/tutorial.pdf?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/site/tutorial.pdf (original)
+++ lucene/nutch/branches/mapred/site/tutorial.pdf Thu Sep 8 12:42:44 2005
@@ -146,10 +146,10 @@
>>
endobj
30 0 obj
-<< /Length 2566 /Filter [ /ASCII85Decode /FlateDecode ]
+<< /Length 2578 /Filter [ /ASCII85Decode /FlateDecode ]
>>
stream
-Gat%%D/\/e&H88.+mdBM+JC)YYPjc1:"NiG\(0:g/41T8[&$/'22\E'J%qaH=[tuF4Tl$aR<Q<...@Flffn>d&dHEG$MPh<EUgp*r_-p*6`#2/0CQqV$DR3Uno_inVWK'd0..1HG(`:\9_3[Y!ksb"Z2e$r"5o;U6RTc;q=e%Gs5nKZ:ZT'];n(i9Dio4X/[X!HUh.HK$OD;L_CIDL(f\^0<g%V;@E]g_S'^>N!7RQ*GSnC**Qso,B(;Mdi(9B;3"#C*794Qtb-J$T=%1WfG;6S?ZMNXqmQ:\pTE)F<S$[gRUXWfl_M88et@i9FD-!=q]g1+&WNB9XH/`d04;DgGVn-ruhh#&2N8<8L[Z/DTSk)bRe2gEhSR2g.9-EI'`["TF&T!WW#?W/k:5*&BI:.1RL+3Ne<`_>s[oL>\e1,.l2%A8"?`(gdO3atA\l1HWh.Z:H<5RQ<\@tPPMUI+7l]Dsnt3/ThEn_$l:m14PoHFM"nWic`aF>F%,k<)\6K&B(U*7p9$ci>>PaR=1,MgCV4a*N\Q6nfI+eoS9EME8OdB]uu'Mu<53mcMDM\\FR2Ku:CY691?$6hKBhI<f95\)]W(X?p^gBrLL(0P[B98.L:r2_#)JVotMLP0hfZVQF1P6a^b-C3c4^+'abuVLW-p<1iocIV%7Sk@/LTXT?Of6dNe;48;!riF7i6_gBe?]Qt>VY'.At>i.i9D;-.5b7kuNrMhWS5P)#4lhRZ0EiV`)s6IrrX@&t)d@OX=2/>e'@>KKMr<JPMf2M~>
+Gat%%=`<%a...@FG>=c_O=e69SOql<?FF)>.fK8)3s(O%0RPdR/Bf2pVO/!i+D>;tQPb>We^Y63ui+W7!(X7+Xk&kmi!_Z4'V68\d+7%R2'F$@F=gbPE(JHps#39HdV!HdM+ihbt]Xm!shH!77^IS.'/-ciuo13q@>2o0Q\VPY.hJN+7=0@Ph+iQ9UE8?`E#];J[R/[A1gJJ$9Ad*6=.;N8DgQCVk\_Hr'=12@uHT/-lB_-I3iI?ln3qK6U:J6(BQn'#9ZN9/DI15HEUG8c)OuJ9\^KWC%9nP1:R:27A9h.s36jFZbYg..An\l_Nt8!<BKe3dqa1`j-U]jK5@"^6ei;;&+ZBfN_HPJJmq]=pWmo-/VV.1<rLjA\lFh/%oOCVj[eLh[0-<k@CsKJNUnZH]g5o-pW+aP'FL$!ad,AK!XNkr&3dWM6QC>43=@YP9%p^Jp,cV-:s:b>TYe*,\Wo[\,h%u*XRujO>SuM-j-KIpYb+PMMIV8*J")9UY_KBM(RuOcP,uWB1]ri"ndBkU_(sU8k_c`)hnU;G!E[,/T8.,/2UNTHQ<[TeMu);D)`I%XcGap$mXYq(qb^3[\K1>ed>*DL7M*Ph>sVn',DER5XVDrhQ^p#0;K&rSmXhTkh6.F2;+;9\JS%n"T[V,-Ju-:=\N1A"a%W;o/N[bGuu?u):l%9@WYLM:PB%!So[r!9JN:ZErTm2A6;+XFU,&C$S92Y`4oRmTkhOScaW?!X'l[5P,>MOc*RHlFC2_Xd5e\EH/=?RS&rXG_6WAjGL,-P/DC/F-dVf5Z%QFbFRp.H85!3,#:L(55@@#-7,hdOoWU@i=G;J!8/_l>D>ObL.o+%9@l*a(*OfH@GXJI2R;6?/9_c@aIXj0!6UBnplT-^t'WKbYlLn/;n*)s_QiL4jOab*)QQol^ChehuRI@qRh.H)LHD1o2A478l/Cr6XQ%XHI0!\c/:YY8rXL9F"28+Nb*@O^-mJ'2=PUVu!,>ZVF:n5-b$(=RbA(fPU8tXg@3%M6@QD(?X(_8dm:q_$XicJMiYk/Z4a7o]<);:Fu-HsYu7P?0nfo)"fCFo+DHedU3@Z7,S(!7oIp@4j;EdfSceGpr_#MmE:"[a1[G^)W<?KAgU&`YYS6HNqF(1M9h(kG1^2`Q/i(]jQl\au]7`R,CeP7Um.O->D8<rGEfnt\OU^W$3$+(:TcGbpr[deNoUH,.[@>BOP7!SQu%7&YpHs(_=;bJoH*]us01RrJ!5K`QP&hqb)_0FLf?LP^b$OMLTj'm4W]&fb#l)p6Zo/rVT_ar\`8CAf#([>:[CQZ[AEm+u-iaOIs9%.js9Tnlg-[u&B)-_=rFFH/VcDPM07S8;Q2q2.aJfCO[:JU.BDU0P2>D:<]b2j@1'>cD%eW'gh:N1kq^M4a"k_B>W5HB;H'Z`VrUCBJ1/\Zdh[6+G(DS?kBg/Ab.V+mn3(6<BfR3gb6&Ml5jD%H'oae7`Kql=qGJ2>D/#3<K^Uon`At8%'u$5OG-cAL6:L(81&b/Tsi2?pRb6h#0UsI_*/eE)5n?B)`4tkV-%ldV+hNh3t6#_X^r1E"DLI9eLXaY1#MJM.S1Rd"Xrf-)dOrCUsa..sF_$reqA1Zg[2A1t<)G(dN3Ed0_FMhs^-BDL7q2c';96<8[=a#;>5"6NS+N^4-!'qM++X]L1=Pf7W<)8@,H\rR3eoQaVBhl(:2H]r:!-f=netWD*%&TVGVI=7&@rGCc?"6T'n)$j?!J_DC/K~>
endstream
endobj
31 0 obj
@@ -219,10 +219,10 @@
37 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 90.0 479.732 233.316 467.732 ]
+/Rect [ 90.0 479.732 275.292 467.732 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
-/A << /URI (http://www.nutch.org/release/)
+/A << /URI (http://lucene.apache.org/nutch/release/)
/S /URI >>
/H /I
>>
@@ -230,7 +230,7 @@
38 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 271.62 466.532 323.616 454.532 ]
+/Rect [ 339.6 466.532 391.596 454.532 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A << /URI (version_control.html)
@@ -241,7 +241,7 @@
39 0 obj
<< /Type /Annot
/Subtype /Link
-/Rect [ 519.948 466.532 537.948 454.532 ]
+/Rect [ 151.68 453.332 169.68 441.332 ]
/C [ 0 0 0 ]
/Border [ 0 0 0 ]
/A << /URI (http://ant.apache.org/)
@@ -250,10 +250,10 @@
>>
endobj
40 0 obj
-<< /Length 2216 /Filter [ /ASCII85Decode /FlateDecode ]
+<< /Length 2213 /Filter [ /ASCII85Decode /FlateDecode ]
>>
stream
-Gau0EgQ(#H&:O:Skc)h(0it+;qbSCAZ:0A>[i"<r2?dcP[Y0o6<MJJh^V6J423]QCS"eOOdF+,H1G`YR\SjC,gO%PV-o$_+IUsFQQ"??PB,R!Q^lP)Q&^PQX9kJd!+_,t2XJp!PM\eCscq*NDBB?HjA1YjCnWTol_(houA1,C[?-/*U)9;KG*!cBlbDMP!)Lk?P$S1^;^IFZ&M4E7B]Ddf[g":\>,3%7n3?]Rnp8u0uI<^A9A8IkUkI'*a7$NIjR<rO89pZ!_=bl4AR>n+9N^d#"l4gd9EYdL(bIuZ3ra)!<F=bUj\.;A"Xa35!OEcLi2]Gq)+n;O/Eau`XIJ%4$H"]r8m*$k(Nn`snLVI:IMn@`uLDQT8qB'c!IX_+^5TXfLSm9$9n@bG*eo?;upJ%/W34N[[EZj89FbH8tq9q=%9BFV1ffC'A)Yt]f4`siX"OculnY_-&ADfh,W!6\:+ZF@r)q+.iRo!&rmrMX;SBJP7Va'H/:\)D^Df8KFlZUo4keSaWeLgQ3^>jGnQlDaF8mF"nh^=2jj:P#.EcF<lM4J+-VWOt+6EYd9.o`Eh`NPbN-aJ]m&]RLFPFCp0DVbjuMaAa7YKl_(mKB(<"!*U5<)>Ns"/YDu)mlU#=9QOQlR42X(7p7F66H?K!ZPgQ#FIRQc;71Qd]V_Q5:QD'M@pX5VRN;6^m--Nj<@R=-hM[\JV?$L`=!P:J`SqGW]$l6#-P`gJ`it$8KK0>->+J(Z@,+@G"W7]I4;H>]2An;B#+sL7Pj[S9&SGQmQA(>[cnCqH"_haK@!BHdq,nkNG>1XgBu8c,VLt;?ZU2LFggC&#@PqVEM/u'_FVcnkD8?TDTAeMR2i%^B0-g>=B+i8Y"f7fodj@=&@(P)`_AOtQB:ckV?^V3WKBq2pf!sfK^<DAI>4arGg@\U&NAEqPq5XT8otd6pteQX(W7@^>Bq]k5V_FX]ULH4`"Jud7IAQ@#%4@Y2k8Ic.e2!@\J?oJ^N3kRjL;6FJFu'(+j,6>P,'!d*WIX^&muc;^ZZ!$+5>i9O5EZ+;mE,f]'\3(Z%i24F@`9brIpsk,qC9:!n`sigYqJedJH3@Ybmna&>8jRN@K#-]Lp._6EM!JJK0g3OTE\h6:6rJe0<l0Z)FMQe*ulPk.A['R>d2O"g'PsR=4"7_ItT;7=qJ,8q@g0TM1lTX,,qP'5%P&NOQ\`rnsmk&,#FB3>+Om74F*LJc7Ucj)Cih]%koI$l>-L.iWlU1";K6'g(oACM@AEGo"@mahrirUnUKse9BR.l7ja[)55F=8']7K`^0WmA3,JS<Wp.3WBn-nBo_"0k+Fj41DVEH+8L((i7g\ele67AHCuG+4QhOZLc!e5aQLjm0bdrOOSH\t?;+LIR"bg;fAZolLQ#Z@aW?QjFRI1@UXg\Z;pBre6_'L'+#lAcS][bDY%4U?.Bb?Fascn11N8,:=h:Q*;qY@Uq-(k9QJG:$S'YgEPMn1&dRPN/R6Fj_%ifT+4r(`AG\Ed'#dN?#_'2O8X]7("pF\V"`g)X&ebsAg`=Xrld2hFA_F[rlAc\<1PBOdN!`LpWdnLS&O1@74qQ+P]S9>Ffh%"R$@Lq<ieo%koP.[$P)7d>flCrs-e0Fqm5J7,Il4[sci+pP#1TdA1LCF#KK`^d>;7c]21[KM.$BsVM[S!qB2VJ]UMpfQ&XMqq(DtP'Ko0c?#6k9c,CH-k9EU&lo6BH[s;TZI9MNn[C!gB\Uik!hF4_>5@[BBk=M$Tb9:TQ/6"Mhn)J-/pnW:hgqC!u4cq.4u@fJZ_=BB$[%db."QjAt5DZ3D'0<gPS1E*J;KR"5Y&`G,BoCuW96?^[Tl$D2lqI5l`'ZC5LW=e8h\%BSa"3.GXc<^T$33dc<f,dVF,#LCcJk@-2Dijmpa8.WbeooA3_h%BX>!j8LnIAjNqd;fh/^7W%3e^Shnm_nZ"G<=p9qoF&6G>hrq9j>OgCB;l=`AL("/_i$>^."tn<JR@:6H#B:J;?oN'M`O/d9u5^U)c;=s5=W.rWhE+XZ'USThjmjCh.=]B58TL*`at[?[gAa8e(YmfPl2oh&[Dgm^BndIH%m;AUt.BBW_^9_c=NHD[8Y?gAPKqoeNCKbJkJY4&_=Ge9>0qh`9:7U$!<pI*jJ&\"\*sLC9/\Xp=5qis9>T*CmeflNXO#&-ZbF;=*DLDr0;'pWY_#<G)H&F[aXdg9iFfjqTPaN;&Ndg:ssnTKW~>
+Gau0E9on$e&A@sBkgX4nQn)%kHROsYfci`0Y8HIHRf]rc>Ja",.T18p^V5p\=[SU?]d\iPLmEeV]U=':aF1Bth;8$pK9:"fp++lYX;oELIu`XCOo-s'!u0CZ[4/1Q018ENX>T]gq;Oh7$8>rdnQG`?@0OcqEW!bDEH'-H$LHF?]W9./8)sB9e`21/,t4*J=5tseIUNDKR+KEc+qlcemaf.X5$OKe;a`_aGpc#4`4e%;]oPsNSrDJ]@oAFp8eJ*7-Th@P%Qj+.:-n_kB'4G?Je:d]P6:i#8s6f8\TaOnh^]YbT&YJZnAE^NX56]47Y0[3m=s1eN'_@2eCq'S?bP,@([[';ap_e@q.cflr07Udh;-pO]_FnGs4HZ4o?2mooPjDBo_isLq0kfDO;IT8DpjT^nE)aPJo[2:$1OON:ZJ+I[8/I:lYI\`*25D&oNb`;8iMRP/^_Z_[(9'9K=Ka"+*kqgZ230C(_jsd;UhM<ib...@2geV9gVkAR>.H+(<eIN)oV:om7h2FEr'VnDFAqEh$=ukEQ*Lp`,aB6R1''nrgSMLA=//DAUC6f*`r?XeoEkA`8L3;*><hCoE",4ZAdOh,CTmS,28!5_dPEr]R>k2Mbh$I,7WdtR[2&GIs`!]k(8hpa&*`UQ3(nm[h8=.-_4bRqsh8B:pjJ"'lFJGp2Z5jO`O@d$3"9>GJL>fjY`Je*I(]^ld#;)\WGW2Jgm1ac5>XmHXOSq;KV1f0$cH4OH[%WIs@Rf+/c\r"/$e`AYi%CL.97[e-\q<pQ5m`<;M'JjIl,dg53S,S_ktNIZO/%qZE=l8*QBh+o>eLuYlWU*$6fq%_##X-/U".Z6+<'TcC@n-[4frDC:q[8*WIQtF:0WjLj>kJIM1WDp(b,63hBQDY:R*J-aS>u,VT97HJ15J8rM[t3fJ*jfY;<d_r[9kc6$=(p-am0'>;chJ^t+=I+%f8Ea-#A2m8G9u8&-d(K'C>Dq"Wln;q%6gW=cODf14,J^Dhl;%bRCf>#LGc^a,"GdsAY(qKq^\&-SfrVB?"LrbeLb*&+R:G+;AZLH/04;EPQuo=<4%A/TPe4F#'gU%^Bg!_MYEnRa-.'?Xme9OMHSkaX?\ZUU-$\u*muL'jkeBBgt?-.p/hREONjjIC2Y<f;`^I"31CT<"u(<Lq822rEY'V1Q;62m<],PTHf.I)`Fm/!DK$'I)Ehb0ol48r8jh/UIatQYNJfT[3NjX3;HTdH*kjl:K";r\MZ<.Pk0?pn"/`h,^@tY&__gH1GUjEk4H_m6na6M_<VhgXc$_6\]m3&VC[0ZhmSE*Lfu1GWA%K$\`m]-hUmd)L,X_1Y<ZS!i75h"I??75>E-)+Xu,[*rI#;]QF(%i@14#A/03_+DjXu^N_0EZL?P15K(c#71Gd0hD1M&PuqeSC>.%#IAT4HrmGJ.1a.I<_kln=&LQjC7JXni$hgD.)t"I]Zm=<c"k.qhj3r!Q$e\S<n!7o"T[D*RP)b2XC2:j@8LDEP?'$Xj'M\7BdtRC'ac<2XCHFANh8=3FK0:0aK6NNe>HPXc087o7<8SY0-m:;T:cQ7OYCI^Ma;Ho2)R@[_CZ+h]aM,JV+Ppg)\,TijSZc.(der`<WOK`F)a\#]R^bIqdBD8.o1#0('@S#MK-RES*l.S2oh-q]R=@?Z@]kejXb5f"a`VlK?#<.rjpo4MY6_9?#XFq.erFeQ@,Yk9P?Ajhp)Ve2f':<OAO@QM0%LJEikNh1fgG&c<oI8g"r-CSPVRu4409isJI>f))?BA6'ZdVp2M50?Sq239\9L(S"Ss[qXe$<ZF'>*K1cqb3*_6r.Tf8.f\)@F%kj!4DR4o!G?t*Z$j6(#E9=e/W5G<UC.af:dUN1I(^mOTR/q+6ehOcm'I"C*K47td8>/B%Ed)aQLU!#oU%!Q].OX1Ao$sr-?lsnl1A@iC-08a;Y-5ILIGFfX*o`3AL*TmCk$+KqgnE/;k0?cCDG[`S:2)_d`.$#EE1mMEVeE':IpRRH*p0?Dp=9itQi7K1[rVj+<Q8*'V$MMA;_+\d'V0$kW`I@,aN*=DY)mts1N?T?g55YYVn"Vl3X[mog/)[n<HE)`.%lMr@p761KC#0q%]m*J.fA41q`plR-(WX78X'b;LF'>Ke&27$OTEa6+*/l>Eop>2t;PNk<d^,VG~>
endstream
endobj
41 0 obj
@@ -556,74 +556,74 @@
xref
0 69
0000000000 65535 f
-0000017160 00000 n
-0000017246 00000 n
-0000017338 00000 n
+0000017176 00000 n
+0000017262 00000 n
+0000017354 00000 n
0000000015 00000 n
0000000071 00000 n
0000000922 00000 n
0000001042 00000 n
0000001137 00000 n
-0000017483 00000 n
+0000017499 00000 n
0000001271 00000 n
-0000017546 00000 n
+0000017562 00000 n
0000001408 00000 n
-0000017612 00000 n
+0000017628 00000 n
0000001545 00000 n
-0000017678 00000 n
+0000017694 00000 n
0000001682 00000 n
-0000017744 00000 n
+0000017760 00000 n
0000001819 00000 n
-0000017809 00000 n
+0000017825 00000 n
0000001956 00000 n
-0000017875 00000 n
+0000017891 00000 n
0000002092 00000 n
-0000017941 00000 n
+0000017957 00000 n
0000002229 00000 n
-0000018006 00000 n
+0000018022 00000 n
0000002366 00000 n
-0000018072 00000 n
+0000018088 00000 n
0000002503 00000 n
-0000018137 00000 n
+0000018153 00000 n
0000002640 00000 n
-0000005299 00000 n
-0000005422 00000 n
-0000005491 00000 n
-0000005684 00000 n
-0000005885 00000 n
-0000006072 00000 n
-0000006248 00000 n
-0000006428 00000 n
-0000006601 00000 n
-0000006777 00000 n
-0000009086 00000 n
-0000009194 00000 n
-0000011358 00000 n
-0000011481 00000 n
-0000011508 00000 n
-0000011678 00000 n
-0000013548 00000 n
-0000013671 00000 n
-0000013698 00000 n
-0000018203 00000 n
-0000013873 00000 n
-0000014036 00000 n
-0000014231 00000 n
-0000014478 00000 n
-0000014716 00000 n
-0000014976 00000 n
-0000015214 00000 n
-0000015427 00000 n
-0000015777 00000 n
-0000016004 00000 n
-0000016231 00000 n
-0000016387 00000 n
-0000016500 00000 n
-0000016610 00000 n
-0000016721 00000 n
-0000016829 00000 n
-0000016935 00000 n
-0000017051 00000 n
+0000005311 00000 n
+0000005434 00000 n
+0000005503 00000 n
+0000005696 00000 n
+0000005897 00000 n
+0000006084 00000 n
+0000006260 00000 n
+0000006450 00000 n
+0000006622 00000 n
+0000006796 00000 n
+0000009102 00000 n
+0000009210 00000 n
+0000011374 00000 n
+0000011497 00000 n
+0000011524 00000 n
+0000011694 00000 n
+0000013564 00000 n
+0000013687 00000 n
+0000013714 00000 n
+0000018219 00000 n
+0000013889 00000 n
+0000014052 00000 n
+0000014247 00000 n
+0000014494 00000 n
+0000014732 00000 n
+0000014992 00000 n
+0000015230 00000 n
+0000015443 00000 n
+0000015793 00000 n
+0000016020 00000 n
+0000016247 00000 n
+0000016403 00000 n
+0000016516 00000 n
+0000016626 00000 n
+0000016737 00000 n
+0000016845 00000 n
+0000016951 00000 n
+0000017067 00000 n
trailer
<<
/Size 69
@@ -631,5 +631,5 @@
/Info 4 0 R
>>
startxref
-18254
+18270
%%EOF
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/analysis/NutchDocumentAnalyzer.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/analysis/NutchDocumentAnalyzer.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/analysis/NutchDocumentAnalyzer.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/analysis/NutchDocumentAnalyzer.java Thu Sep 8 12:42:44 2005
@@ -13,20 +13,25 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-
package org.apache.nutch.analysis;
+// JDK imports
+import java.io.Reader;
+import java.io.IOException;
+
+// Lucene imports
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Token;
-import java.io.Reader;
-import java.io.IOException;
-/** The analyzer used for Nutch documents. Uses the JavaCC-defined lexical
- * analyzer {@link NutchDocumentTokenizer}, with no stop list. This keeps it
- * consistent with query parsing. */
-public class NutchDocumentAnalyzer extends Analyzer {
+
+/**
+ * The analyzer used for Nutch documents.
+ * Uses the JavaCC-defined lexical analyzer {@link NutchDocumentTokenizer},
+ * with no stop list. This keeps it consistent with query parsing.
+ */
+public class NutchDocumentAnalyzer extends NutchAnalyzer {
/** Analyzer used to index textual content. */
private static class ContentAnalyzer extends Analyzer {
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/clustering/OnlineClusterer.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/clustering/OnlineClusterer.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/clustering/OnlineClusterer.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/clustering/OnlineClusterer.java Thu Sep 8 12:42:44 2005
@@ -23,8 +23,8 @@
* algorithms.
*
* <p>By the term <b>online</b> search results clustering we will understand
- * a clusterer that works on a set of {@link Hit}s retrieved for a user's query
- * and produces a set of {@link Clusters} that can be displayed to help
+ * a clusterer that works on a set of {@link HitDetails} retrieved for a user's
+ * query and produces a set of {@link HitsCluster} that can be displayed to help
* the user gain insight in the topics found in the result.</p>
*
* <p>Other clustering options include predefined categories and off-line
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/clustering/OnlineClustererFactory.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/clustering/OnlineClustererFactory.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/clustering/OnlineClustererFactory.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/clustering/OnlineClustererFactory.java Thu Sep 8 12:42:44 2005
@@ -63,7 +63,7 @@
// not found, fallback to the default, if available.
}
- Extension[] extensions = X_POINT.getExtentens();
+ Extension[] extensions = X_POINT.getExtensions();
if (extensions.length > 0) {
LOG.info("Using the first clustering extension found: "
+ extensions[0].getId());
@@ -76,7 +76,7 @@
private static Extension findExtension(String name)
throws PluginRuntimeException {
- Extension[] extensions = X_POINT.getExtentens();
+ Extension[] extensions = X_POINT.getExtensions();
for (int i = 0; i < extensions.length; i++) {
Extension extension = extensions[i];
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/fs/FileUtil.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/fs/FileUtil.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/fs/FileUtil.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/fs/FileUtil.java Thu Sep 8 12:42:44 2005
@@ -47,7 +47,7 @@
}
File dstParent = dst.getParentFile();
- if (! nfs.exists(dstParent)) {
+ if ((dstParent != null) && (!nfs.exists(dstParent))) {
nfs.mkdirs(dstParent);
}
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/fs/NDFSFileSystem.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/fs/NDFSFileSystem.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/fs/NDFSFileSystem.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/fs/NDFSFileSystem.java Thu Sep 8 12:42:44 2005
@@ -19,7 +19,6 @@
import java.io.*;
import java.net.*;
import java.util.*;
-import java.text.*;
import org.apache.nutch.io.*;
import org.apache.nutch.ndfs.*;
@@ -44,15 +43,18 @@
*/
public NDFSFileSystem(InetSocketAddress namenode) throws IOException {
this.ndfs = new NDFSClient(namenode);
- this.name = namenode.getHostName()+":"+namenode.getPort();
+ this.name = namenode.getHostName() + ":" + namenode.getPort();
}
public String getName() { return name; }
private UTF8 getPath(File file) {
- if (!file.isAbsolute())
- file = new File(HOME_DIR+file.getPath());
- return new UTF8(file.getPath());
+ File f = file;
+ String path = getNDFSPath(file);
+ if (!path.startsWith(NDFSFile.NDFS_FILE_SEPARATOR)) {
+ f = new File(HOME_DIR, path);
+ }
+ return new UTF8(getNDFSPath(f));
}
/**
@@ -291,5 +293,29 @@
*/
public NDFSClient getClient() {
return ndfs;
+ }
+
+ private String getNDFSPath(File f) {
+ List l = new ArrayList();
+ l.add(f.getName());
+ File parent = f.getParentFile();
+ while (parent != null) {
+ l.add(parent.getName());
+ parent = parent.getParentFile();
+ }
+ StringBuffer path = new StringBuffer();
+ String fname = (String) l.get(l.size() - 1);
+ if (!"".equals(fname)) {
+ path.append(fname); //handle not absolute paths
+ } else {
+ if (l.size() == 1)
+ path.append(NDFSFile.NDFS_FILE_SEPARATOR); //handle root path
+ }
+ for (int i = l.size() - 2; i >= 0; i--) {
+ fname = (String) l.get(i);
+ path.append(NDFSFile.NDFS_FILE_SEPARATOR);
+ path.append(fname);
+ }
+ return path.toString();
}
}
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/indexer/IndexSegment.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/indexer/IndexSegment.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/indexer/IndexSegment.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/indexer/IndexSegment.java Thu Sep 8 12:42:44 2005
@@ -16,25 +16,20 @@
package org.apache.nutch.indexer;
-import org.apache.nutch.pagedb.*;
-import org.apache.nutch.linkdb.*;
import org.apache.nutch.fetcher.*;
import org.apache.nutch.parse.*;
import org.apache.nutch.analysis.NutchDocumentAnalyzer;
-import org.apache.nutch.db.*;
-import org.apache.nutch.io.*;
import org.apache.nutch.fs.*;
import org.apache.nutch.segment.SegmentReader;
import org.apache.nutch.util.*;
-
-import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import java.util.logging.*;
-import java.util.*;
import java.io.*;
+import org.apache.nutch.analysis.AnalyzerFactory;
+import org.apache.nutch.analysis.NutchAnalyzer;
/** Creates an index for the output corresponding to a single fetcher run. */
public class IndexSegment {
@@ -149,7 +144,12 @@
doc = IndexingFilters.filter(doc, parse, fetcherOutput);
// add the document to the index
- writer.addDocument(doc);
+ NutchAnalyzer analyzer = AnalyzerFactory.get(doc.get("lang"));
+ LOG.info(" Indexing [" + doc.getField("url").stringValue() + "]" +
+ " with analyzer " + analyzer +
+ " (" + doc.get("lang") + ")");
+ //LOG.info(" Doc is " + doc);
+ writer.addDocument(doc, analyzer);
if (count > 0 && count % LOG_STEP == 0) {
curTime = System.currentTimeMillis();
LOG.info(" Processed " + count + " records (" +
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/indexer/IndexingFilters.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/indexer/IndexingFilters.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/indexer/IndexingFilters.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/indexer/IndexingFilters.java Thu Sep 8 12:42:44 2005
@@ -34,7 +34,7 @@
.getExtensionPoint(IndexingFilter.X_POINT_ID);
if (point == null)
throw new RuntimeException(IndexingFilter.X_POINT_ID+" not found.");
- Extension[] extensions = point.getExtentens();
+ Extension[] extensions = point.getExtensions();
HashMap filterMap = new HashMap();
for (int i = 0; i < extensions.length; i++) {
Extension extension = extensions[i];
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/FileSplit.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/FileSplit.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/FileSplit.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/FileSplit.java Thu Sep 8 12:42:44 2005
@@ -26,8 +26,8 @@
import org.apache.nutch.fs.NutchFileSystem;
/** A section of an input file. Returned by {@link
- * InputFormat#getSplits(File[], int)} and passed to
- * InputFormat#getRecordReader(FileSplit). */
+ * InputFormat#getSplits(NutchFileSystem, JobConf, int)} and passed to
+ * InputFormat#getRecordReader(NutchFileSystem, FileSplit, JobConf). */
public class FileSplit implements Writable {
private File file;
private long start;
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/MapOutputFile.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/MapOutputFile.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/MapOutputFile.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/MapOutputFile.java Thu Sep 8 12:42:44 2005
@@ -53,7 +53,7 @@
/** Create a local reduce input file name.
* @param mapTaskId a map task id
- * @param partition a reduce partition
+ * @param reduceTaskId a reduce task id
*/
public static File getInputFile(String mapTaskId, String reduceTaskId) {
File taskDir = new File(LOCAL_DIR, reduceTaskId);
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/RecordReader.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/RecordReader.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/RecordReader.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/RecordReader.java Thu Sep 8 12:42:44 2005
@@ -22,7 +22,7 @@
import org.apache.nutch.io.WritableComparable;
import org.apache.nutch.io.Writable;
-/** Reads key/value pairs from an input file {@link InputFormat.Split}.
+/** Reads key/value pairs from an input file {@link FileSplit}.
* Implemented by {@link InputFormat} implementations. */
public interface RecordReader {
/** Reads the next key/value pair.
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/package.html
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/package.html?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/package.html (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/mapred/package.html Thu Sep 8 12:42:44 2005
@@ -6,7 +6,7 @@
<p>Applications implement {@link org.apache.nutch.mapReduce.Mapper} and
{@link org.apache.nutch.mapReduce.Reducer} interfaces. These are submitted
-as a {@link org.apache.nutch.mapReduce.MapReduceJob} and are applied to data
+as a {@link org.apache.nutch.mapred.JobConf} and are applied to data
stored in a {@link org.apache.nutch.fs.NutchFileSystem}.</p>
<p>See <a href="http://labs.google.com/papers/mapreduce.html">Google's
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/FSDirectory.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/FSDirectory.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/FSDirectory.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/FSDirectory.java Thu Sep 8 12:42:44 2005
@@ -102,11 +102,11 @@
/**
*/
- INode addNode(String target, Block blocks[]) {
+ INode addNode(String target, Block blks[]) {
if (getNode(target) != null) {
return null;
} else {
- String parentName = new File(target).getParent();
+ String parentName = NDFSFile.getNDFSParent(target);
if (parentName == null) {
return null;
}
@@ -116,7 +116,7 @@
return null;
} else {
String targetName = new File(target).getName();
- INode newItem = new INode(targetName, parentNode, blocks);
+ INode newItem = new INode(targetName, parentNode, blks);
parentNode.children.put(targetName, newItem);
return newItem;
}
@@ -462,7 +462,7 @@
waitForReady();
// Always do an implicit mkdirs for parent directory tree
- mkdirs(new File(src.toString()).getParent());
+ mkdirs(NDFSFile.getNDFSParent(src.toString()));
if (unprotectedAddFile(src, blocks)) {
logEdit(OP_ADD, src, new ArrayWritable(Block.class, blocks));
return true;
@@ -683,13 +683,13 @@
Vector v = new Vector();
// The dir itself
- File f = new File(src);
- v.add(f.getPath());
+ v.add(src);
// All its parents
- while (f.getParent() != null) {
- f = new File(f.getParent());
- v.add(f.getPath());
+ String parent = NDFSFile.getNDFSParent(src);
+ while (parent != null) {
+ v.add(parent);
+ parent = NDFSFile.getNDFSParent(parent);
}
// Now go backwards through list of dirs, creating along
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/NDFSFile.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/NDFSFile.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/NDFSFile.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/NDFSFile.java Thu Sep 8 12:42:44 2005
@@ -16,8 +16,6 @@
package org.apache.nutch.ndfs;
import java.io.*;
-import java.net.*;
-import java.util.*;
/*****************************************************************
@@ -29,6 +27,9 @@
public class NDFSFile extends File {
NDFSFileInfo info;
+ /** Separator used in NDFS filenames. */
+ public static final String NDFS_FILE_SEPARATOR = "/";
+
/**
*/
public NDFSFile(NDFSFileInfo info) {
@@ -75,5 +76,23 @@
*/
public long getContentsLength() {
return info.getContentsLen();
+ }
+
+ /**
+ * Retrieving parent path from NDFS path string
+ * @param path - NDFS path
+ * @return - parent path of NDFS path, or null if no parent exist.
+ */
+ public static String getNDFSParent(String path) {
+ if (path == null)
+ return null;
+ if (NDFS_FILE_SEPARATOR.equals(path))
+ return null;
+ int index = path.lastIndexOf(NDFS_FILE_SEPARATOR);
+ if (index == -1)
+ return null;
+ if (index == 0)
+ return NDFS_FILE_SEPARATOR;
+ return path.substring(0, index);
}
}
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/NDFSFileInfo.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/NDFSFileInfo.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/NDFSFileInfo.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/ndfs/NDFSFileInfo.java Thu Sep 8 12:42:44 2005
@@ -16,10 +16,8 @@
package org.apache.nutch.ndfs;
import org.apache.nutch.io.*;
-import org.apache.nutch.util.*;
import java.io.*;
-import java.util.*;
/******************************************************
* NDFSFileInfo tracks info about remote files, including
@@ -50,7 +48,7 @@
/**
*/
public String getPath() {
- return new File(path.toString()).getPath();
+ return path.toString();
}
/**
@@ -62,7 +60,7 @@
/**
*/
public String getParent() {
- return new File(path.toString()).getParent();
+ return NDFSFile.getNDFSParent(path.toString());
}
/**
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/net/URLFilterChecker.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/net/URLFilterChecker.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/net/URLFilterChecker.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/net/URLFilterChecker.java Thu Sep 8 12:42:44 2005
@@ -19,7 +19,6 @@
import org.apache.nutch.plugin.Extension;
import org.apache.nutch.plugin.ExtensionPoint;
import org.apache.nutch.plugin.PluginRepository;
-import org.apache.nutch.plugin.PluginRuntimeException;
import org.apache.nutch.util.LogFormatter;
@@ -27,7 +26,6 @@
import java.io.BufferedReader;
import java.io.InputStreamReader;
-import java.io.IOException;
/**
* Checke one given filter or all filters.
@@ -51,7 +49,7 @@
if (point == null)
throw new RuntimeException(URLFilter.X_POINT_ID+" not found.");
- Extension[] extensions = point.getExtentens();
+ Extension[] extensions = point.getExtensions();
for (int i = 0; i < extensions.length; i++) {
Extension extension = extensions[i];
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/net/URLFilters.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/net/URLFilters.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/net/URLFilters.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/net/URLFilters.java Thu Sep 8 12:42:44 2005
@@ -43,7 +43,7 @@
if (point == null)
throw new RuntimeException(URLFilter.X_POINT_ID+" not found.");
- Extension[] extensions = point.getExtentens();
+ Extension[] extensions = point.getExtensions();
HashMap filterMap = new HashMap();
for (int i = 0; i < extensions.length; i++) {
Extension extension = extensions[i];
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/ontology/OntologyFactory.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/ontology/OntologyFactory.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/ontology/OntologyFactory.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/ontology/OntologyFactory.java Thu Sep 8 12:42:44 2005
@@ -62,7 +62,7 @@
// not found, fallback to the default, if available.
}
- Extension[] extensions = X_POINT.getExtentens();
+ Extension[] extensions = X_POINT.getExtensions();
if (extensions.length > 0) {
LOG.info("Using the first ontology extension found: "
+ extensions[0].getId());
@@ -76,7 +76,7 @@
private static Extension findExtension(String name)
throws PluginRuntimeException {
- Extension[] extensions = X_POINT.getExtentens();
+ Extension[] extensions = X_POINT.getExtensions();
for (int i = 0; i < extensions.length; i++) {
Extension extension = extensions[i];
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/HtmlParseFilters.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/HtmlParseFilters.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/HtmlParseFilters.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/HtmlParseFilters.java Thu Sep 8 12:42:44 2005
@@ -31,7 +31,7 @@
.getExtensionPoint(HtmlParseFilter.X_POINT_ID);
if (point == null)
throw new RuntimeException(HtmlParseFilter.X_POINT_ID+" not found.");
- Extension[] extensions = point.getExtentens();
+ Extension[] extensions = point.getExtensions();
CACHE = new HtmlParseFilter[extensions.length];
for (int i = 0; i < extensions.length; i++) {
Extension extension = extensions[i];
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/Parse.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/Parse.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/Parse.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/Parse.java Thu Sep 8 12:42:44 2005
@@ -17,7 +17,7 @@
package org.apache.nutch.parse;
/** The result of parsing a page's raw content.
- * @see Parser#getParse(FetcherOutput,Content)
+ * @see Parser#getParse(Content)
*/
public interface Parse {
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/ParserFactory.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/ParserFactory.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/ParserFactory.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/parse/ParserFactory.java Thu Sep 8 12:42:44 2005
@@ -98,7 +98,7 @@
//LOG.fine("findExtension: contentType="+contentType+" suffix="+suffix);
- Extension[] extensions = X_POINT.getExtentens();
+ Extension[] extensions = X_POINT.getExtensions();
// first look for a content-type match
if (contentType != null) {
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/Extension.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/Extension.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/Extension.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/Extension.java Thu Sep 8 12:42:44 2005
@@ -17,8 +17,8 @@
package org.apache.nutch.plugin;
import java.util.HashMap;
/**
- * A <code>Extension</code> is a kind of listener descriptor that will be
- * installed on a concret <code>ExtensionPoint</code> that act as kind of
+ * An <code>Extension</code> is a kind of listener descriptor that will be
+ * installed on a concrete <code>ExtensionPoint</code> that acts as kind of
* Publisher.
*
* @author joa23
@@ -40,7 +40,7 @@
public Extension(PluginDescriptor pDescriptor, String pExtensionPoint,
String pId, String pExtensionClass) {
fAttributes = new HashMap();
- setDiscriptor(pDescriptor);
+ setDescriptor(pDescriptor);
setExtensionPoint(pExtensionPoint);
setId(pId);
setClazz(pExtensionClass);
@@ -140,7 +140,7 @@
Class extensionClazz = loader.loadClass(getClazz());
// lazy loading of Plugin in case there is no instance of the plugin
// already.
- PluginRepository.getInstance().getPluginInstance(getDiscriptor());
+ PluginRepository.getInstance().getPluginInstance(getDescriptor());
Object object = extensionClazz.newInstance();
return object;
} catch (ClassNotFoundException e) {
@@ -152,21 +152,29 @@
}
}
}
+
+ /**
+ * @deprecated Use #{getDescriptor()} instead.
+ */
+ public PluginDescriptor getDiscriptor() {
+ return getDescriptor();
+ }
+
/**
* return the plugin descriptor.
*
* @return PluginDescriptor
*/
- public PluginDescriptor getDiscriptor() {
+ public PluginDescriptor getDescriptor() {
return fDescriptor;
}
/**
* Sets the plugin descriptor and is only used until model creation at system
* start up.
*
- * @return PluginDescriptor
+ * @param pDescriptor
*/
- public void setDiscriptor(PluginDescriptor pDescriptor) {
+ public void setDescriptor(PluginDescriptor pDescriptor) {
fDescriptor = pDescriptor;
}
}
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/ExtensionPoint.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/ExtensionPoint.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/ExtensionPoint.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/ExtensionPoint.java Thu Sep 8 12:42:44 2005
@@ -70,8 +70,7 @@
/**
* Sets the extensionPointId.
*
- * @param extension point id
- * The extensionPointId to set
+ * @param pId extension point id
*/
private void setId(String pId) {
ftId = pId;
@@ -79,8 +78,7 @@
/**
* Sets the extension point name.
*
- * @param extensionPointName
- * The extensionPointName to set
+ * @param pName
*/
private void setName(String pName) {
fName = pName;
@@ -88,8 +86,7 @@
/**
* Sets the schema.
*
- * @param schema
- * The schema to set
+ * @param pSchema
*/
private void setSchema(String pSchema) {
fSchema = pSchema;
@@ -107,8 +104,18 @@
*
* @return Extension[]
*/
- public Extension[] getExtentens() {
+ public Extension[] getExtensions() {
return (Extension[]) fExtensions.toArray(new Extension[fExtensions
.size()]);
+ }
+
+ /**
+ * Returns a array of extensions that lsiten to this extension point
+ *
+ * @return Extension[]
+ * @deprecated Use the correctly spelled #{getExtensions} method instead.
+ */
+ public Extension[] getExtentens() {
+ return getExtensions();
}
}
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/Plugin.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/Plugin.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/Plugin.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/Plugin.java Thu Sep 8 12:42:44 2005
@@ -17,7 +17,7 @@
package org.apache.nutch.plugin;
/**
* A nutch-plugin is an container for a set of custom logic that provide
- * extensions to the nutch core functionality or a other plugin that proides a
+ * extensions to the nutch core functionality or another plugin that provides an
* API for extending. A plugin can provide one or a set of extensions.
* Extensions are components that can be dynamically installed as a kind of
* listener to extension points. Extension points are a kind of publisher that
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginDescriptor.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginDescriptor.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginDescriptor.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginDescriptor.java Thu Sep 8 12:42:44 2005
@@ -196,7 +196,7 @@
/**
* Adds a exported library with a relative path to the plugin directory.
*
- * @param plibPath
+ * @param pLibPath
*/
public void addExportedLibRelative(String pLibPath)
throws MalformedURLException {
@@ -220,7 +220,7 @@
return (URL[]) fExportedLibs.toArray(new URL[0]);
}
/**
- * Adds a not exported library with a plugin directory relativ path.
+ * Adds a not exported library with a plugin directory relative path.
*
* @param pLibPath
*/
@@ -278,7 +278,8 @@
return list;
}
/**
- * @param list
+ * @param pLibs
+ * @param pDescriptor
*/
private void collectLibs(ArrayList pLibs, PluginDescriptor pDescriptor) {
String[] pPluginIds = pDescriptor.getDependencies();
@@ -295,7 +296,7 @@
}
}
/**
- * Returns a internationalizabel resource string. The resource bundles could
+ * Returns a I18N'd resource string. The resource bundles could
* be stored in root directory of a plugin in the well know i18n file name
* conventions.
*
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginManifestParser.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginManifestParser.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginManifestParser.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginManifestParser.java Thu Sep 8 12:42:44 2005
@@ -168,7 +168,7 @@
}
/**
- * @param document
+ * @param pDocument
* @throws MalformedURLException
*/
private static PluginDescriptor parsePlugin(Document pDocument, String pPath)
@@ -189,12 +189,38 @@
parseExtension(rootElement, pluginDescriptor);
parseExtensionPoints(rootElement, pluginDescriptor);
parseLibraries(rootElement, pluginDescriptor);
+ parseRequires(rootElement, pluginDescriptor);
return pluginDescriptor;
}
/**
- * @param rootElement
- * @param pluginDescriptor
+ * @param pRootElement
+ * @param pDescriptor
+ * @throws MalformedURLException
+ */
+ private static void parseRequires(Element pRootElement,
+ PluginDescriptor pDescriptor)
+ throws MalformedURLException {
+
+ NodeList nodelist = pRootElement.getElementsByTagName("requires");
+ if (nodelist.getLength() > 0) {
+
+ Element requires = (Element) nodelist.item(0);
+
+ NodeList imports = requires.getElementsByTagName("import");
+ for (int i=0; i<imports.getLength(); i++) {
+ Element anImport = (Element) imports.item(i);
+ String plugin = anImport.getAttribute("plugin");
+ if (plugin != null) {
+ pDescriptor.addDependency(plugin);
+ }
+ }
+ }
+ }
+
+ /**
+ * @param pRootElement
+ * @param pDescriptor
* @throws MalformedURLException
*/
private static void parseLibraries(Element pRootElement,
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginRepository.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginRepository.java?rev=279605&r1=279604&r2=279605&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginRepository.java (original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/plugin/PluginRepository.java Thu Sep 8 12:42:44 2005
@@ -31,7 +31,7 @@
* At system boot up a repositority is builded by parsing the mainifest files of
* all plugins. Plugins that require not existing other plugins are not
* registed. For each plugin a plugin descriptor instance will be created. The
- * descriptor represent all meta information about a plugin. So a plugin
+ * descriptor represents all meta information about a plugin. So a plugin
* instance will be created later when it is required, this allow lazy plugin
* loading.
*
@@ -62,7 +62,7 @@
}
/**
- * @param fRegisteredPlugins
+ * @param pRegisteredPlugins
*/
private void installExtensions(ArrayList pRegisteredPlugins)
throws PluginRuntimeException {
@@ -95,7 +95,7 @@
boolean available = true;
for (int j = 0; j < dependencyIDs.length; j++) {
String id = dependencyIDs[j];
- if (!dependencyIsAvailabel(id, pLoadedPlugins)) {
+ if (!dependencyIsAvailable(id, pLoadedPlugins)) {
available = false;
//LOG.fine("Skipping " + descriptor.getName());
break;
@@ -121,7 +121,7 @@
* @param pLoadedPlugins
* @return boolean
*/
- private boolean dependencyIsAvailabel(String id, ArrayList pLoadedPlugins) {
+ private boolean dependencyIsAvailable(String id, ArrayList pLoadedPlugins) {
if (pLoadedPlugins != null && id != null) {
for (int i = 0; i < pLoadedPlugins.size(); i++) {
PluginDescriptor descriptor = (PluginDescriptor) pLoadedPlugins