Modified: lucene/hadoop/trunk/docs/index.pdf URL: http://svn.apache.org/viewvc/lucene/hadoop/trunk/docs/index.pdf?rev=608973&r1=608972&r2=608973&view=diff ============================================================================== --- lucene/hadoop/trunk/docs/index.pdf (original) +++ lucene/hadoop/trunk/docs/index.pdf Fri Jan 4 11:52:39 2008 @@ -5,10 +5,10 @@ /Producer (FOP 0.20.5) >> endobj 5 0 obj -<< /Length 1161 /Filter [ /ASCII85Decode /FlateDecode ] +<< /Length 1271 /Filter [ /ASCII85Decode /FlateDecode ] >> stream -Gat=+9lldX&[EMAIL PROTECTED]:M<CfZ:A(!2N3n'KDp.Puk%g:'6'5SXPilSs=ps]A"&5Ne]0&$'V/ut8I?<U]R)57TfBXtQBnIo"-D(HV<[EMAIL PROTECTED],0a'r[Np=Qfp5JV1*T-'*n>.m5$s7j8C;#LR(.^-q?1t5W_NlFg3&aKs]X8!eqL%0%P"V`Q)r40s4N9S/U!&M-n.8#RfX?TFPpt^L)-7#ATMO$7s9,IV,Zk(e)HuWp!il[l?=d7Y.Kpo92kMl?'We$3rXeML!ptW2^jrNk=rigX^iX=mk8P=>.3WMdiTV7Y1_l&[EMAIL PROTECTED]:j>DYq"GjiB+?4/$R'JQHq88nor0[)&[EMAIL PROTECTED]/>b9f:'TXFn+"VbD.LJ_3/PJhm<Jlk\[%j==_K%ZOUs$e.M_'Tj%Nl!WRe\]#X0W,*YCZE?4pF1r[WB+&HDMN2C'NN0M8[&Y2<[EMAIL PROTECTED]<a%e0Cf;Un0K,j_BZa=UNpBf^ieB)3b2?ee>6o_:(37dG0\2e,[EMAIL PROTECTED],9Z/^!FUS\_OJ<MEI8LSEafI^X0Dj:,Gf2g2gl"27rcgTn*8*X^JN_#"%V2.)li'FbXqO7X:H%A5$nX]&43b>XJM="e^0`GhsFJFX.[5:g&77eITU;[EMAIL PROTECTED])XZ9+)9,irBS/T3NjNT!]dAjZl`HW9'A+MTHTub)a-`Un0p:dAY65g?SK2m[NS%'DlPHI69+Fl2PED.D&A6QP'[EMAIL PROTECTED]'[EMAIL PROTECTED](i6\"Ea&%>W<\W+F#(kP3HgV#)^Q1I&J,+lG&,I=bN&[EMAIL PROTECTED]:b8$cAd'(!n^%DA3001L.2A$kp!fbtLYLTZ*`NKNtV1d*)4oE0nUJ;2uWot&0d>,c?e&?EQodTQ5XmK`/tNY'ICLJ_HO=^<2q:$>C J*6o1ub;0)-jD`Zil':2\5#\]JDGTNOX8=OB`[V/GH3UrcY:U07.7]4]l\:,YkKPBVUoqU$IQ#g<7<#%]Q'PJ,>N3P)&oP.Gq5Sk=gbooo`&1Toh-([t#=!b4,[EMAIL PROTECTED](N8aX&LCKC5#CIrrIqX;Xs~> +Gat=,9lo&I&[EMAIL PROTECTED]:i98BA#RCJSG]]B88Z1soZ"A;qHCu]Xig:>nIRrLK++R^#Os3>1I'@dJIJ^6p==j8fja;=B&7q6%e]&cp?fVd*F^.?,T8Nd2'9$<[EMAIL PROTECTED])RH?b5E8#nj3-q>nl6$l/XpTYjB7U#2DJ`5aL]1n_>krCqDX_Z`8kLOe"[EMAIL PROTECTED],e.F;>&*r*K8?L'/JHa"F/[EMAIL PROTECTED]"[EMAIL PROTECTED]<7_Uaa4JR([U"+Z]A0;%Y^Vlf2oX'lRg>%k"/n`h!r&i9c@;pcT2&*"IK,6GcPJS!6IYZ_eb&Tl\K2McG+JgK/@ghekfJ*l5-EW'Cl>k3=;4SbI2F>3)(m6WVD3qHI,Zl6(d`I"[EMAIL PROTECTED]"b`(!0,h:g/23,BTO;W*g$1b6krDh3Wng_^G:[EMAIL PROTECTED]@`k]e02ZAJED.A*Q:[EMAIL PROTECTED](KW-Z/BqO(^P_/`:[K5sE1Oc8-;)a<<sE4aQ^`&09LX'_$N%j63=#Z58B\l?8]_DR[:*DGYI4;!>o?A"e$gq6iTl#'-<OA>(T.e>H/;,E1mrl2I9=H(hMm^3s[Y9?cN:",K,@eZC&%QEY3M+k\5CPfH4=+?jt8l[akl3<23!Sf@>f^l>lu%tK5$B/$<?%Y><S%l"\"jSMM-dO]i"m8Z0j35d`nYEWl41#+_<"-!lY3b]N?83b&7e0R*X2Q?WM<+?2`#bg]8e#KRWm6Uj.VcS<-p.KMO!jCm_bB.Q$e"2S(cYY^T!Oss&knl1;o*hL<Ca#`ME8]&[EMAIL PROTECTED]:4s'<s5dA/H#n4dhi9/q[qL(KkaiJHljD(+>T.Z6-A_dnld,f0J#C$=*CraEI4/lq#C;&U(k6iZB5Lso=kL\ZlckWFL&2!>K;Ikp1r'#I89%0_.BV*':2n(66'QYt&3KP:O#%)'r q$O(qXMP%4/[EMAIL PROTECTED]@FU)hho7?;V`)g*="S`0"[EMAIL PROTECTED](k0oB67>;ADe\Cbk6q=Wm"[EMAIL PROTECTED]/B^OX`k?P9ngL_\XKKk)%7C080C^7'[EMAIL PROTECTED];W<g*3DY1KrS1t;H*+]Iog+63QhnJB;e7TcfcfP#W&KL%IX/[EMAIL PROTECTED]/T2?R%a"W,=;n=F'@0Sh)BmEf^DbVnkX5?Cr7[6%?[`VTn;JU*XrX3-<_$U~> endstream endobj 6 0 obj @@ -30,6 +30,7 @@ 13 0 R 14 0 R 15 0 R +16 0 R ] endobj 8 0 obj @@ -90,10 +91,10 @@ 13 0 obj << /Type /Annot /Subtype /Link -/Rect [ 108.0 489.4 154.992 477.4 ] +/Rect [ 108.0 489.4 227.304 477.4 ] /C [ 0 0 0 ] /Border [ 0 0 0 ] -/A << /URI (api/index.html) +/A << /URI (native_libraries.html) /S /URI >> /H /I >> @@ -101,10 +102,10 @@ 14 0 obj << /Type /Annot /Subtype /Link -/Rect [ 108.0 476.2 132.0 464.2 ] +/Rect [ 108.0 476.2 154.992 464.2 ] /C [ 0 0 0 ] /Border [ 0 0 0 ] -/A << /URI (http://wiki.apache.org/lucene-hadoop/) +/A << /URI (api/index.html) /S /URI >> /H /I >> @@ -115,33 +116,44 @@ /Rect [ 108.0 463.0 132.0 451.0 ] /C [ 0 0 0 ] /Border [ 0 0 0 ] -/A << /URI (http://wiki.apache.org/lucene-hadoop/FAQ) +/A << /URI (http://wiki.apache.org/lucene-hadoop/) /S /URI >> /H /I >> endobj 16 0 obj +<< /Type /Annot +/Subtype /Link +/Rect [ 108.0 449.8 132.0 437.8 ] +/C [ 0 0 0 ] +/Border [ 0 0 0 ] +/A << /URI (http://wiki.apache.org/lucene-hadoop/FAQ) +/S /URI >> +/H /I +>> +endobj +17 0 obj << /Type /Font /Subtype /Type1 /Name /F3 /BaseFont /Helvetica-Bold /Encoding /WinAnsiEncoding >> endobj -17 0 obj +18 0 obj << /Type /Font /Subtype /Type1 /Name /F5 /BaseFont /Times-Roman /Encoding /WinAnsiEncoding >> endobj -18 0 obj +19 0 obj << /Type /Font /Subtype /Type1 /Name /F1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >> endobj -19 0 obj +20 0 obj << /Type /Font /Subtype /Type1 /Name /F2 @@ -160,37 +172,38 @@ endobj 3 0 obj << -/Font << /F3 16 0 R /F5 17 0 R /F1 18 0 R /F2 19 0 R >> +/Font << /F3 17 0 R /F5 18 0 R /F1 19 0 R /F2 20 0 R >> /ProcSet [ /PDF /ImageC /Text ] >> endobj xref -0 20 +0 21 0000000000 65535 f -0000003354 00000 n -0000003412 00000 n -0000003462 00000 n +0000003640 00000 n +0000003698 00000 n +0000003748 00000 n 0000000015 00000 n 0000000071 00000 n -0000001324 00000 n -0000001444 00000 n -0000001517 00000 n -0000001716 00000 n -0000001878 00000 n -0000002044 00000 n -0000002208 00000 n -0000002376 00000 n -0000002538 00000 n -0000002721 00000 n -0000002907 00000 n -0000003020 00000 n -0000003130 00000 n -0000003238 00000 n +0000001434 00000 n +0000001554 00000 n +0000001634 00000 n +0000001833 00000 n +0000001995 00000 n +0000002161 00000 n +0000002325 00000 n +0000002493 00000 n +0000002662 00000 n +0000002824 00000 n +0000003007 00000 n +0000003193 00000 n +0000003306 00000 n +0000003416 00000 n +0000003524 00000 n trailer << -/Size 20 +/Size 21 /Root 2 0 R /Info 4 0 R >> startxref -3574 +3860 %%EOF
Modified: lucene/hadoop/trunk/docs/linkmap.html URL: http://svn.apache.org/viewvc/lucene/hadoop/trunk/docs/linkmap.html?rev=608973&r1=608972&r2=608973&view=diff ============================================================================== --- lucene/hadoop/trunk/docs/linkmap.html (original) +++ lucene/hadoop/trunk/docs/linkmap.html Fri Jan 4 11:52:39 2008 @@ -1,11 +1,11 @@ -<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> <html> <head> <META http-equiv="Content-Type" content="text/html; charset=UTF-8"> <meta content="Apache Forrest" name="Generator"> -<meta name="Forrest-version" content="0.7"> +<meta name="Forrest-version" content="0.8"> <meta name="Forrest-skin-name" content="pelt"> -<title>Site Linkmap</title> +<title>Site Linkmap Table of Contents</title> <link type="text/css" href="skin/basic.css" rel="stylesheet"> <link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet"> <link media="print" type="text/css" href="skin/print.css" rel="stylesheet"> @@ -16,46 +16,91 @@ <body onload="init()"> <script type="text/javascript">ndeSetTextSize();</script> <div id="top"> +<!--+ + |breadtrail + +--> <div class="breadtrail"> <a href="http://www.apache.org/">Apache</a> > <a href="http://lucene.apache.org/">Lucene</a> > <a href="http://lucene.apache.org/hadoop/">Hadoop</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script> </div> +<!--+ + |header + +--> <div class="header"> +<!--+ + |start group logo + +--> <div class="grouplogo"> <a href="http://lucene.apache.org/"><img class="logoImage" alt="Lucene" src="images/lucene_green_150.gif" title="Apache Lucene"></a> </div> +<!--+ + |end group logo + +--> +<!--+ + |start Project Logo + +--> <div class="projectlogo"> <a href="http://lucene.apache.org/hadoop/"><img class="logoImage" alt="Hadoop" src="images/hadoop-logo.jpg" title="Scalable Computing Platform"></a> </div> +<!--+ + |end Project Logo + +--> +<!--+ + |start Search + +--> <div class="searchbox"> <form action="http://www.google.com/search" method="get" class="roundtopsmall"> <input value="lucene.apache.org" name="sitesearch" type="hidden"><input onFocus="getBlank (this, 'Search the site with google');" size="25" name="q" id="query" type="text" value="Search the site with google"> - <input attr="value" name="Search" value="Search" type="submit"> + <input name="Search" value="Search" type="submit"> </form> </div> +<!--+ + |end search + +--> +<!--+ + |start Tabs + +--> <ul id="tabs"> <li> -<a class="base-not-selected" href="http://lucene.apache.org/hadoop/">Project</a> +<a class="unselected" href="http://lucene.apache.org/hadoop/">Project</a> </li> <li> -<a class="base-not-selected" href="http://wiki.apache.org/lucene-hadoop">Wiki</a> +<a class="unselected" href="http://wiki.apache.org/lucene-hadoop">Wiki</a> </li> <li class="current"> -<a class="base-selected" href="index.html">Hadoop 0.16 Documentation</a> +<a class="selected" href="index.html">Hadoop 0.16 Documentation</a> </li> </ul> +<!--+ + |end Tabs + +--> </div> </div> <div id="main"> <div id="publishedStrip"> +<!--+ + |start Subtabs + +--> <div id="level2tabs"></div> +<!--+ + |end Endtabs + +--> <script type="text/javascript"><!-- -document.write("<text>Last Published:</text> " + document.lastModified); +document.write("Last Published: " + document.lastModified); // --></script> </div> +<!--+ + |breadtrail + +--> <div class="breadtrail"> - + </div> +<!--+ + |start Menu, mainarea + +--> +<!--+ + |start Menu + +--> <div id="menu"> <div onclick="SwitchMenu('menu_1.1', 'skin/')" id="menu_1.1Title" class="menutitle">Documentation</div> <div id="menu_1.1" class="menuitemgroup"> @@ -75,6 +120,9 @@ <a href="mapred_tutorial.html">Map-Reduce Tutorial</a> </div> <div class="menuitem"> +<a href="native_libraries.html">Native Hadoop Libraries</a> +</div> +<div class="menuitem"> <a href="streaming.html">Streaming</a> </div> <div class="menuitem"> @@ -96,100 +144,108 @@ <div id="credit"></div> <div id="roundbottom"> <img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div> +<!--+ + |alternative credits + +--> <div id="credit2"></div> </div> +<!--+ + |end Menu + +--> +<!--+ + |start content + +--> <div id="content"> <div title="Portable Document Format" class="pdflink"> <a class="dida" href="linkmap.pdf"><img alt="PDF -icon" src="skin/images/pdfdoc.gif" class="skin"><br> PDF</a> </div> -<h1>Site Linkmap</h1> -<div id="minitoc-area"> -<ul class="minitoc"> -<li> -<a href="#Table+of+Contents">Table of Contents</a> -</li> -</ul> -</div> -<a name="N10007"></a><a name="Table+of+Contents"></a> -<h2 class="h3">Table of Contents</h2> -<div class="section"> +<h1>Site Linkmap Table of Contents</h1> +<p> + This is a map of the complete site and its structure. + </p> <ul> <li> -<a href="">Hadoop</a> _________________________ <em>site</em> +<a>Hadoop</a> ___________________ <em>site</em> </li> <ul> <ul> <li> -<a href="">Documentation</a> _________________________ <em>docs</em> +<a>Documentation</a> ___________________ <em>docs</em> </li> <ul> <ul> <li> -<a href="index.html">Overview</a> _________________________ <em>overview</em> +<a href="index.html">Overview</a> ___________________ <em>overview</em> </li> </ul> <ul> <li> -<a href="quickstart.html">Quickstart</a> _________________________ <em>quickstart</em> +<a href="quickstart.html">Quickstart</a> ___________________ <em>quickstart</em> </li> </ul> <ul> <li> -<a href="cluster_setup.html">Cluster Setup</a> _________________________ <em>setup</em> +<a href="cluster_setup.html">Cluster Setup</a> ___________________ <em>setup</em> </li> </ul> <ul> <li> -<a href="hdfs_design.html">HDFS Architecture</a> _________________________ <em>hdfs</em> +<a href="hdfs_design.html">HDFS Architecture</a> ___________________ <em>hdfs</em> </li> </ul> <ul> <li> -<a href="mapred_tutorial.html">Map-Reduce Tutorial</a> _________________________ <em>mapred</em> +<a href="mapred_tutorial.html">Map-Reduce Tutorial</a> ___________________ <em>mapred</em> </li> </ul> <ul> <li> -<a href="streaming.html">Streaming</a> _________________________ <em>streaming</em> +<a href="native_libraries.html">Native Hadoop Libraries</a> ___________________ <em>mapred</em> </li> </ul> <ul> <li> -<a href="hod.html">Hadoop On Demand</a> _________________________ <em>hod</em> +<a href="streaming.html">Streaming</a> ___________________ <em>streaming</em> </li> </ul> <ul> <li> -<a href="api/index.html">API Docs</a> _________________________ <em>api</em> +<a href="hod.html">Hadoop On Demand</a> ___________________ <em>hod</em> </li> </ul> <ul> <li> -<a href="http://wiki.apache.org/lucene-hadoop/">Wiki</a> _________________________ <em>wiki</em> +<a href="api/index.html">API Docs</a> ___________________ <em>api</em> </li> </ul> <ul> <li> -<a href="http://wiki.apache.org/lucene-hadoop/FAQ">FAQ</a> _________________________ <em>faq</em> +<a href="http://wiki.apache.org/lucene-hadoop/">Wiki</a> ___________________ <em>wiki</em> </li> </ul> <ul> <li> -<a href="http://lucene.apache.org/hadoop/mailing_lists.html">Mailing Lists</a> _________________________ <em>lists</em> +<a href="http://wiki.apache.org/lucene-hadoop/FAQ">FAQ</a> ___________________ <em>faq</em> +</li> +</ul> + +<ul> +<li> +<a href="http://lucene.apache.org/hadoop/mailing_lists.html">Mailing Lists</a> ___________________ <em>lists</em> </li> </ul> @@ -202,19 +258,27 @@ </ul> </ul> </div> -</div> +<!--+ + |end content + +--> <div class="clearboth"> </div> </div> <div id="footer"> +<!--+ + |start bottomstrip + +--> <div class="lastmodified"> <script type="text/javascript"><!-- -document.write("<text>Last Published:</text> " + document.lastModified); +document.write("Last Published: " + document.lastModified); // --></script> </div> <div class="copyright"> Copyright © 2007 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a> </div> +<!--+ + |end bottomstrip + +--> </div> </body> </html> Modified: lucene/hadoop/trunk/docs/linkmap.pdf URL: http://svn.apache.org/viewvc/lucene/hadoop/trunk/docs/linkmap.pdf?rev=608973&r1=608972&r2=608973&view=diff ============================================================================== --- lucene/hadoop/trunk/docs/linkmap.pdf (original) +++ lucene/hadoop/trunk/docs/linkmap.pdf Fri Jan 4 11:52:39 2008 @@ -5,10 +5,10 @@ /Producer (FOP 0.20.5) >> endobj 5 0 obj -<< /Length 357 /Filter [ /ASCII85Decode /FlateDecode ] +<< /Length 881 /Filter [ /ASCII85Decode /FlateDecode ] >> stream -GauI0_,>n>&;KY!METC?CGrC"Nj`F.NYeV(W<]6G1/^A&*T(0o)+Zp_BQ?ZCAG=hhs0WHJ>9?gp&kjq=\>2I.5nM+G'#`g5(eF;:#g<UH]j9#u/%AG;)K*4.U3]$MbmIdn4:EnQ1r1dMX;T+jcNKHEPnq3rPum.l5-:kLX86_r0p''/O]3Qe#m5V<OW1G%7,)fBqF^G*>hr$Mh_DcrLsR56#bIK6F`53R[DXtdUdiT?fEY&K$uH3ZGS9>i8i:[EMAIL PROTECTED]&tLL\*oq4a5lV52V!1.TC[]-^*T]rUc(4)(7LD>dW)PJ3tGFOJ<P&[llGkcDt]YAB9Cf7*hB0p>c~> +GatUrhbVu\&[EMAIL PROTECTED]&fE>[EMAIL PROTECTED],[EMAIL PROTECTED])lRIa5L1mke<t=p9FQLd8OS+T%KW&@c(TJBSg^`6O&N_'"\&\coj/el%E9E'g;OX;kNgl=%k[rC"fs8oJ!PqXKuR[&A(f%"<j$X&3I/';[EMAIL PROTECTED]@[EMAIL PROTECTED]'\]$jUi5cQpQW$4e`aThFB]-_B?)7`/:gCj_L>,`HRDpSm'a,062DMe"j`I>YqXZ6s*=Lp3t1"+,S>c&[EMAIL PROTECTED](q\_P<Ru'4HfJ;0C+`[T",H"HjXPU1)/s7:(brcMB\-%SIZi]92AHU-JA\(8g,kiL6NkCRA2gX7*ZE:=4eI_E*V38P4gu)[EMAIL PROTECTED]@+4:[kd=mHh1f9\S1U)^mViitQ#pqb0/']Js9#Hbs?b'df-V.\$s:,VZ%a:pnA'dn*(Z)m,/O^,u-6ni$*"P-ic>QFr_\8s(Er6X=cUeKUVt[1tjAqTT`EPK13uDdMd'[EMAIL PROTECTED]@5+pri'[Dq3!r1ABru0e\$EUF83$hS)2^8af*Sl.N^g)6E"fFUIXEcVmTQ$H"pQ!0TmEE0\'j'_UNO!Brl*p`No7HP9"G[N+NAVGRZ8_ieaud(aOrfZ3qWF,\XVT`c].FqQ8]o(nXXUnj"q37ULeD`Aa,([?a,N]rrOFof9oQLTNF79h*[g``FIL0G.e>S&[EMAIL PROTECTED]"SMGeMJQdTKib!1FgIPf)?e`Yh7$Mt&,dqo"a?UA'(-.d=[JO1Oqa1&[EMAIL PROTECTED]<_f2`Yn;n:]RbdZ2=URui!c)alKj^#b*]uS:$2`g?GZUJB,[EMAIL PROTECTED]"SEp~> endstream endobj 6 0 obj @@ -17,143 +17,78 @@ /MediaBox [ 0 0 612 792 ] /Resources 3 0 R /Contents 5 0 R -/Annots 7 0 R >> endobj 7 0 obj -[ -8 0 R -] -endobj -8 0 obj -<< /Type /Annot -/Subtype /Link -/Rect [ 102.0 559.666 195.992 547.666 ] -/C [ 0 0 0 ] -/Border [ 0 0 0 ] -/A 9 0 R -/H /I ->> -endobj -10 0 obj -<< /Length 858 /Filter [ /ASCII85Decode /FlateDecode ] - >> -stream -Gatn%?#Q2d'Sc)P'u"K;iqhDKRC:;MBiWmkBc#M\\_na3"B$qUp?uWX'MM_'-'m>*/H!3m#G8mo&&#<7"IMIX_Ms>[EMAIL PROTECTED]>W;tlur&hgb'J'Nnf2"_UTB\Va2uWD<Sf+)eneD!+iE,JHkWN+s>55GUMGaY,+TQ<G?P!u<!=B;(]fY\q#/UA(([EMAIL PROTECTED](1Djq*bSX%*hoOebp?\h$,4\%9G%)o7Nm(/`iV0hbdCd;Pb5H+<UdB1,8Vg&0bj#,Tr4%q#]TBj"c[q]hOhK8Y42Fo1=l'\A`_m^5"*$"n#$>hT!0Qd`#.ZT4a;j"B$cT7eoo,MG?_+^J/oR-.,(o<+4q[YpOOpeYAm&7EBj)hBom+X4$4+YE$"Ke]_OElnLna%;a3gFpaH:a+O6jo]gJ)mO=Jk['L!!10(#\_GUc`r.4MnhL+6Xg8>piR;6qII+N?Q3?9NL9O8toSOm%`Pd,f8?6'@n:\(dkNtp'r'O'mfCchZ];G%-gAM63c-h1:V*ID:_bF>TJ^=7Lp`H/A#_(cfMm.([_P`rA`>2F^J(n2j20=A<(!3W(X,h%F2NYU')j<9ot-%ZpKc].'$PPpr2'[CH=pKs"%LQ-VM,bb;].ue>0UhsO^n+'[EMAIL PROTECTED]'&+;n0&`eZ1"<)$7*(O%LLiPlfQ[1+B$'A$<"3A&%3FeK2"K`28]_i&k_$*1q%]!HD9*b'?pnPDN1SjJLtSCG(-o847ja-E8C,T&InS)1@>QcQua)[EMAIL PROTECTED],H5<fCkI?QY6F)ZhSaM-l5t,\(c8Xlg(!arOYHkYU=J2uP:&CUR/tH+2p1pjAf]VZE39,F8~> -endstream -endobj -11 0 obj -<< /Type /Page -/Parent 1 0 R -/MediaBox [ 0 0 612 792 ] -/Resources 3 0 R -/Contents 10 0 R ->> -endobj -13 0 obj -<< - /Title (\376\377\0\61\0\40\0\124\0\141\0\142\0\154\0\145\0\40\0\157\0\146\0\40\0\103\0\157\0\156\0\164\0\145\0\156\0\164\0\163) - /Parent 12 0 R - /A 9 0 R ->> endobj -14 0 obj << /Type /Font /Subtype /Type1 /Name /F3 /BaseFont /Helvetica-Bold /Encoding /WinAnsiEncoding >> endobj -15 0 obj +8 0 obj << /Type /Font /Subtype /Type1 /Name /F5 /BaseFont /Times-Roman /Encoding /WinAnsiEncoding >> endobj -16 0 obj +9 0 obj << /Type /Font /Subtype /Type1 /Name /F6 /BaseFont /Times-Italic /Encoding /WinAnsiEncoding >> endobj -17 0 obj +10 0 obj << /Type /Font /Subtype /Type1 /Name /F1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >> endobj -18 0 obj +11 0 obj << /Type /Font /Subtype /Type1 /Name /F2 /BaseFont /Helvetica-Oblique /Encoding /WinAnsiEncoding >> endobj -19 0 obj -<< /Type /Font -/Subtype /Type1 -/Name /F7 -/BaseFont /Times-Bold -/Encoding /WinAnsiEncoding >> -endobj 1 0 obj << /Type /Pages -/Count 2 -/Kids [6 0 R 11 0 R ] >> +/Count 1 +/Kids [6 0 R ] >> endobj 2 0 obj << /Type /Catalog /Pages 1 0 R - /Outlines 12 0 R - /PageMode /UseOutlines >> endobj 3 0 obj << -/Font << /F3 14 0 R /F5 15 0 R /F1 17 0 R /F6 16 0 R /F2 18 0 R /F7 19 0 R >> +/Font << /F3 7 0 R /F5 8 0 R /F1 10 0 R /F6 9 0 R /F2 11 0 R >> /ProcSet [ /PDF /ImageC /Text ] >> endobj -9 0 obj -<< -/S /GoTo -/D [11 0 R /XYZ 85.0 659.0 null] ->> -endobj -12 0 obj -<< - /First 13 0 R - /Last 13 0 R ->> endobj xref -0 20 +0 12 0000000000 65535 f -0000002701 00000 n -0000002766 00000 n -0000002858 00000 n +0000001704 00000 n +0000001762 00000 n +0000001812 00000 n 0000000015 00000 n 0000000071 00000 n -0000000519 00000 n -0000000639 00000 n -0000000664 00000 n -0000002992 00000 n -0000000799 00000 n -0000001749 00000 n -0000003055 00000 n -0000001857 00000 n -0000002034 00000 n -0000002147 00000 n -0000002257 00000 n -0000002368 00000 n -0000002476 00000 n -0000002592 00000 n +0000001043 00000 n +0000001149 00000 n +0000001261 00000 n +0000001370 00000 n +0000001480 00000 n +0000001588 00000 n trailer << -/Size 20 +/Size 12 /Root 2 0 R /Info 4 0 R >> startxref -3106 +1932 %%EOF Modified: lucene/hadoop/trunk/docs/mapred_tutorial.html URL: http://svn.apache.org/viewvc/lucene/hadoop/trunk/docs/mapred_tutorial.html?rev=608973&r1=608972&r2=608973&view=diff ============================================================================== --- lucene/hadoop/trunk/docs/mapred_tutorial.html (original) +++ lucene/hadoop/trunk/docs/mapred_tutorial.html Fri Jan 4 11:52:39 2008 @@ -1,9 +1,9 @@ -<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> +<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> <html> <head> <META http-equiv="Content-Type" content="text/html; charset=UTF-8"> <meta content="Apache Forrest" name="Generator"> -<meta name="Forrest-version" content="0.7"> +<meta name="Forrest-version" content="0.8"> <meta name="Forrest-skin-name" content="pelt"> <title>Hadoop Map-Reduce Tutorial</title> <link type="text/css" href="skin/basic.css" rel="stylesheet"> @@ -16,46 +16,91 @@ <body onload="init()"> <script type="text/javascript">ndeSetTextSize();</script> <div id="top"> +<!--+ + |breadtrail + +--> <div class="breadtrail"> <a href="http://www.apache.org/">Apache</a> > <a href="http://lucene.apache.org/">Lucene</a> > <a href="http://lucene.apache.org/hadoop/">Hadoop</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script> </div> +<!--+ + |header + +--> <div class="header"> +<!--+ + |start group logo + +--> <div class="grouplogo"> <a href="http://lucene.apache.org/"><img class="logoImage" alt="Lucene" src="images/lucene_green_150.gif" title="Apache Lucene"></a> </div> +<!--+ + |end group logo + +--> +<!--+ + |start Project Logo + +--> <div class="projectlogo"> <a href="http://lucene.apache.org/hadoop/"><img class="logoImage" alt="Hadoop" src="images/hadoop-logo.jpg" title="Scalable Computing Platform"></a> </div> +<!--+ + |end Project Logo + +--> +<!--+ + |start Search + +--> <div class="searchbox"> <form action="http://www.google.com/search" method="get" class="roundtopsmall"> <input value="lucene.apache.org" name="sitesearch" type="hidden"><input onFocus="getBlank (this, 'Search the site with google');" size="25" name="q" id="query" type="text" value="Search the site with google"> - <input attr="value" name="Search" value="Search" type="submit"> + <input name="Search" value="Search" type="submit"> </form> </div> +<!--+ + |end search + +--> +<!--+ + |start Tabs + +--> <ul id="tabs"> <li> -<a class="base-not-selected" href="http://lucene.apache.org/hadoop/">Project</a> +<a class="unselected" href="http://lucene.apache.org/hadoop/">Project</a> </li> <li> -<a class="base-not-selected" href="http://wiki.apache.org/lucene-hadoop">Wiki</a> +<a class="unselected" href="http://wiki.apache.org/lucene-hadoop">Wiki</a> </li> <li class="current"> -<a class="base-selected" href="index.html">Hadoop 0.16 Documentation</a> +<a class="selected" href="index.html">Hadoop 0.16 Documentation</a> </li> </ul> +<!--+ + |end Tabs + +--> </div> </div> <div id="main"> <div id="publishedStrip"> +<!--+ + |start Subtabs + +--> <div id="level2tabs"></div> +<!--+ + |end Endtabs + +--> <script type="text/javascript"><!-- -document.write("<text>Last Published:</text> " + document.lastModified); +document.write("Last Published: " + document.lastModified); // --></script> </div> +<!--+ + |breadtrail + +--> <div class="breadtrail"> - + </div> +<!--+ + |start Menu, mainarea + +--> +<!--+ + |start Menu + +--> <div id="menu"> <div onclick="SwitchMenu('menu_selected_1.1', 'skin/')" id="menu_selected_1.1Title" class="menutitle" style="background-image: url('skin/images/chapter_open.gif');">Documentation</div> <div id="menu_selected_1.1" class="selectedmenuitemgroup" style="display: block;"> @@ -75,6 +120,9 @@ <div class="menupagetitle">Map-Reduce Tutorial</div> </div> <div class="menuitem"> +<a href="native_libraries.html">Native Hadoop Libraries</a> +</div> +<div class="menuitem"> <a href="streaming.html">Streaming</a> </div> <div class="menuitem"> @@ -96,8 +144,17 @@ <div id="credit"></div> <div id="roundbottom"> <img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div> +<!--+ + |alternative credits + +--> <div id="credit2"></div> </div> +<!--+ + |end Menu + +--> +<!--+ + |start content + +--> <div id="content"> <div title="Portable Document Format" class="pdflink"> <a class="dida" href="mapred_tutorial.pdf"><img alt="PDF -icon" src="skin/images/pdfdoc.gif" class="skin"><br> @@ -206,6 +263,9 @@ <li> <a href="#JobControl">JobControl</a> </li> +<li> +<a href="#Data+Compression">Data Compression</a> +</li> </ul> </li> </ul> @@ -214,7 +274,7 @@ <a href="#Example%3A+WordCount+v2.0">Example: WordCount v2.0</a> <ul class="minitoc"> <li> -<a href="#Source+Code-N10A91">Source Code</a> +<a href="#Source+Code-N10B1F">Source Code</a> </li> <li> <a href="#Sample+Runs">Sample Runs</a> @@ -1513,9 +1573,14 @@ individual task.</p> <p> <a href="api/org/apache/hadoop/mapred/TextInputFormat.html"> - TextInputFormat</a> is the default <span class="codefrag">InputFormat</span>. - </p> -<a name="N108E9"></a><a name="InputSplit"></a> + TextInputFormat</a> is the default <span class="codefrag">InputFormat</span>.</p> +<p>If <span class="codefrag">TextInputFormat</span> is the <span class="codefrag">InputFormat</span> for a + given job, the framework detects input-files with the <em>.gz</em> and + <em>.lzo</em> extensions and automatically decompresses them using the + appropriate <span class="codefrag">CompressionCodec</span>. However, it must be noted that + compressed files with the above extensions cannot be <em>split</em> and + each compressed file is processed in its entirety by a single mapper.</p> +<a name="N108FE"></a><a name="InputSplit"></a> <h4>InputSplit</h4> <p> <a href="api/org/apache/hadoop/mapred/InputSplit.html"> @@ -1529,7 +1594,7 @@ FileSplit</a> is the default <span class="codefrag">InputSplit</span>. It sets <span class="codefrag">map.input.file</span> to the path of the input file for the logical split.</p> -<a name="N1090E"></a><a name="RecordReader"></a> +<a name="N10923"></a><a name="RecordReader"></a> <h4>RecordReader</h4> <p> <a href="api/org/apache/hadoop/mapred/RecordReader.html"> @@ -1541,7 +1606,7 @@ for processing. <span class="codefrag">RecordReader</span> thus assumes the responsibility of processing record boundaries and presents the tasks with keys and values.</p> -<a name="N10931"></a><a name="Job+Output"></a> +<a name="N10946"></a><a name="Job+Output"></a> <h3 class="h4">Job Output</h3> <p> <a href="api/org/apache/hadoop/mapred/OutputFormat.html"> @@ -1566,7 +1631,7 @@ <p> <span class="codefrag">TextOutputFormat</span> is the default <span class="codefrag">OutputFormat</span>.</p> -<a name="N1095A"></a><a name="Task+Side-Effect+Files"></a> +<a name="N1096F"></a><a name="Task+Side-Effect+Files"></a> <h4>Task Side-Effect Files</h4> <p>In some applications, component tasks need to create and/or write to side-files, which differ from the actual job-output files.</p> @@ -1592,7 +1657,7 @@ JobConf.getOutputPath()</a>, and the framework will promote them similarly for succesful task-attempts, thus eliminating the need to pick unique paths per task-attempt.</p> -<a name="N1098F"></a><a name="RecordWriter"></a> +<a name="N109A4"></a><a name="RecordWriter"></a> <h4>RecordWriter</h4> <p> <a href="api/org/apache/hadoop/mapred/RecordWriter.html"> @@ -1600,9 +1665,9 @@ pairs to an output file.</p> <p>RecordWriter implementations write the job outputs to the <span class="codefrag">FileSystem</span>.</p> -<a name="N109A6"></a><a name="Other+Useful+Features"></a> +<a name="N109BB"></a><a name="Other+Useful+Features"></a> <h3 class="h4">Other Useful Features</h3> -<a name="N109AC"></a><a name="Counters"></a> +<a name="N109C1"></a><a name="Counters"></a> <h4>Counters</h4> <p> <span class="codefrag">Counters</span> represent global counters, defined either by @@ -1616,7 +1681,7 @@ Reporter.incrCounter(Enum, long)</a> in the <span class="codefrag">map</span> and/or <span class="codefrag">reduce</span> methods. These counters are then globally aggregated by the framework.</p> -<a name="N109D7"></a><a name="DistributedCache"></a> +<a name="N109EC"></a><a name="DistributedCache"></a> <h4>DistributedCache</h4> <p> <a href="api/org/apache/hadoop/filecache/DistributedCache.html"> @@ -1648,7 +1713,7 @@ <span class="codefrag">DistributedCache</span> tracks the modification timestamps of the cached files. Clearly the cache files should not be modified by the application or externally while the job is executing.</p> -<a name="N10A11"></a><a name="Tool"></a> +<a name="N10A26"></a><a name="Tool"></a> <h4>Tool</h4> <p>The <a href="api/org/apache/hadoop/util/Tool.html">Tool</a> interface supports the handling of generic Hadoop command-line options. @@ -1688,7 +1753,7 @@ </span> </p> -<a name="N10A43"></a><a name="IsolationRunner"></a> +<a name="N10A58"></a><a name="IsolationRunner"></a> <h4>IsolationRunner</h4> <p> <a href="api/org/apache/hadoop/mapred/IsolationRunner.html"> @@ -1712,21 +1777,73 @@ <p> <span class="codefrag">IsolationRunner</span> will run the failed task in a single jvm, which can be in the debugger, over precisely the same input.</p> -<a name="N10A76"></a><a name="JobControl"></a> +<a name="N10A8B"></a><a name="JobControl"></a> <h4>JobControl</h4> <p> <a href="api/org/apache/hadoop/mapred/jobcontrol/package-summary.html"> JobControl</a> is a utility which encapsulates a set of Map-Reduce jobs and their dependencies.</p> +<a name="N10A98"></a><a name="Data+Compression"></a> +<h4>Data Compression</h4> +<p>Hadoop Map-Reduce provides facilities for the application-writer to + specify compression for both intermediate map-outputs and the + job-outputs i.e. output of the reduces. It also comes bundled with + <a href="api/org/apache/hadoop/io/compress/CompressionCodec.html"> + CompressionCodec</a> implementations for the + <a href="http://www.zlib.net/">zlib</a> and <a href="http://www.oberhumer.com/opensource/lzo/">lzo</a> compression + algorithms. The <a href="http://www.gzip.org/">gzip</a> file format is also + supported.</p> +<p>Hadoop also provides native implementations of the above compression + codecs for reasons of both performance (zlib) and non-availability of + Java libraries (lzo). More details on their usage and availability are + available <a href="native_libraries.html">here</a>.</p> +<a name="N10AB8"></a><a name="Intermediate+Outputs"></a> +<h5>Intermediate Outputs</h5> +<p>Applications can control compression of intermediate map-outputs + via the + <a href="api/org/apache/hadoop/mapred/JobConf.html#setCompressMapOutput(boolean)"> + JobConf.setCompressMapOutput(boolean)</a> api and the + <span class="codefrag">CompressionCodec</span> to be used via the + <a href="api/org/apache/hadoop/mapred/JobConf.html#setMapOutputCompressorClass(java.lang.Class)"> + JobConf.setMapOutputCompressorClass(Class)</a> api. Since + the intermediate map-outputs are always stored in the + <a href="api/org/apache/hadoop/io/SequenceFile.html">SequenceFile</a> + format, the + <a href="api/org/apache/hadoop/io/SequenceFile.CompressionType.html"> + SequenceFile.CompressionType</a> (i.e. + <a href="api/org/apache/hadoop/io/SequenceFile.CompressionType.html#RECORD"> + RECORD</a> / + <a href="api/org/apache/hadoop/io/SequenceFile.CompressionType.html#BLOCK"> + BLOCK</a> - defaults to <span class="codefrag">RECORD</span>) can be specified via the + <a href="api/org/apache/hadoop/mapred/JobConf.html#setMapOutputCompressionType(org.apache.hadoop.io.SequenceFile.CompressionType)"> + JobConf.setMapOutputCompressionType(SequenceFile.CompressionType)</a> + api.</p> +<a name="N10AE4"></a><a name="Job+Outputs"></a> +<h5>Job Outputs</h5> +<p>Applications can control compression of job-outputs via the + <a href="api/org/apache/hadoop/mapred/OutputFormatBase.html#setCompressOutput(org.apache.hadoop.mapred.JobConf,%20boolean)"> + OutputFormatBase.setCompressOutput(JobConf, boolean)</a> api and the + <span class="codefrag">CompressionCodec</span> to be used can be specified via the + <a href="api/org/apache/hadoop/mapred/OutputFormatBase.html#setOutputCompressorClass(org.apache.hadoop.mapred.JobConf,%20java.lang.Class)"> + OutputFormatBase.setOutputCompressorClass(JobConf, Class)</a> api.</p> +<p>If the job outputs are to be stored in the + <a href="api/org/apache/hadoop/mapred/SequenceFileOutputFormat.html"> + SequenceFileOutputFormat</a>, the required + <span class="codefrag">SequenceFile.CompressionType</span> (i.e. <span class="codefrag">RECORD</span> / + <span class="codefrag">BLOCK</span> - defaults to <span class="codefrag">RECORD</span>)can be specified + via the + <a href="api/org/apache/hadoop/mapred/SequenceFileOutputFormat.html#setOutputCompressionType(org.apache.hadoop.mapred.JobConf,%20org.apache.hadoop.io.SequenceFile.CompressionType)"> + SequenceFileOutputFormat.setOutputCompressionType(JobConf, + SequenceFile.CompressionType)</a> api.</p> </div> -<a name="N10A85"></a><a name="Example%3A+WordCount+v2.0"></a> +<a name="N10B13"></a><a name="Example%3A+WordCount+v2.0"></a> <h2 class="h3">Example: WordCount v2.0</h2> <div class="section"> <p>Here is a more complete <span class="codefrag">WordCount</span> which uses many of the features provided by the Map-Reduce framework we discussed so far:</p> -<a name="N10A91"></a><a name="Source+Code-N10A91"></a> +<a name="N10B1F"></a><a name="Source+Code-N10B1F"></a> <h3 class="h4">Source Code</h3> <table class="ForrestTable" cellspacing="1" cellpadding="4"> @@ -2904,7 +3021,7 @@ </tr> </table> -<a name="N111C3"></a><a name="Sample+Runs"></a> +<a name="N11251"></a><a name="Sample+Runs"></a> <h3 class="h4">Sample Runs</h3> <p>Sample text-files as input:</p> <p> @@ -3069,7 +3186,7 @@ <br> </p> -<a name="N11293"></a><a name="Salient+Points"></a> +<a name="N11321"></a><a name="Salient+Points"></a> <h3 class="h4">Salient Points</h3> <p>The second version of <span class="codefrag">WordCount</span> improves upon the previous one by using some features offered by the Map-Reduce framework: @@ -3114,18 +3231,27 @@ </div> +<!--+ + |end content + +--> <div class="clearboth"> </div> </div> <div id="footer"> +<!--+ + |start bottomstrip + +--> <div class="lastmodified"> <script type="text/javascript"><!-- -document.write("<text>Last Published:</text> " + document.lastModified); +document.write("Last Published: " + document.lastModified); // --></script> </div> <div class="copyright"> Copyright © 2007 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a> </div> +<!--+ + |end bottomstrip + +--> </div> </body> </html>