svn commit: r379403 - in /lucene/nutch/trunk: conf/ src/java/org/apache/nutch/parse/ src/plugin/creativecommons/src/test/org/creativecommons/nutch/ src/plugin/languageidentifier/src/java/org/apache/nu
Author: jerome Date: Tue Feb 21 01:54:21 2006 New Revision: 379403 URL: http://svn.apache.org/viewcvs?rev=379403view=rev Log: NUTCH-140, parse-plugin.xml can now use extension-id and plugin-id Modified: lucene/nutch/trunk/conf/parse-plugins.dtd lucene/nutch/trunk/conf/parse-plugins.xml lucene/nutch/trunk/src/java/org/apache/nutch/parse/ParsePluginList.java lucene/nutch/trunk/src/java/org/apache/nutch/parse/ParsePluginsReader.java lucene/nutch/trunk/src/java/org/apache/nutch/parse/ParseUtil.java lucene/nutch/trunk/src/java/org/apache/nutch/parse/ParserFactory.java lucene/nutch/trunk/src/plugin/creativecommons/src/test/org/creativecommons/nutch/TestCCParseFilter.java lucene/nutch/trunk/src/plugin/languageidentifier/src/java/org/apache/nutch/analysis/lang/LanguageIdentifier.java lucene/nutch/trunk/src/plugin/languageidentifier/src/test/org/apache/nutch/analysis/lang/TestHTMLLanguageParser.java lucene/nutch/trunk/src/plugin/parse-ext/src/test/org/apache/nutch/parse/ext/TestExtParser.java lucene/nutch/trunk/src/plugin/parse-mp3/src/test/org/apache/nutch/parse/mp3/TestMP3Parser.java lucene/nutch/trunk/src/plugin/parse-msexcel/src/test/org/apache/nutch/parse/msexcel/TestMSExcelParser.java lucene/nutch/trunk/src/plugin/parse-mspowerpoint/src/test/org/apache/nutch/parse/mspowerpoint/TestMSPowerPointParser.java lucene/nutch/trunk/src/plugin/parse-msword/src/test/org/apache/nutch/parse/msword/TestMSWordParser.java lucene/nutch/trunk/src/plugin/parse-pdf/src/test/org/apache/nutch/parse/pdf/TestPdfParser.java lucene/nutch/trunk/src/plugin/parse-rss/src/test/org/apache/nutch/parse/rss/TestRSSParser.java lucene/nutch/trunk/src/plugin/parse-rtf/src/test/org/apache/nutch/parse/rtf/TestRTFParser.java lucene/nutch/trunk/src/plugin/parse-zip/src/test/org/apache/nutch/parse/zip/TestZipParser.java lucene/nutch/trunk/src/test/org/apache/nutch/parse/TestParserFactory.java lucene/nutch/trunk/src/test/org/apache/nutch/parse/parse-plugin-test.xml Modified: lucene/nutch/trunk/conf/parse-plugins.dtd URL: http://svn.apache.org/viewcvs/lucene/nutch/trunk/conf/parse-plugins.dtd?rev=379403r1=379402r2=379403view=diff == --- lucene/nutch/trunk/conf/parse-plugins.dtd (original) +++ lucene/nutch/trunk/conf/parse-plugins.dtd Tue Feb 21 01:54:21 2006 @@ -1,7 +1,12 @@ -!ELEMENT parse-plugins (mimeType+) +!ELEMENT parse-plugins (mimeType+,aliases) !ELEMENT mimeType (plugin+) !ATTLIST mimeType name CDATA #REQUIRED !ELEMENT plugin EMPTY !ATTLIST plugin id CDATA #REQUIRED -!ATTLIST plugin order CDATA '' \ No newline at end of file +!ATTLIST plugin order CDATA '' + +!ELEMENT aliases (alias+) +!ELEMENT alias EMPTY +!ATTLIST alias name CDATA #REQUIRED +!ATTLIST alias extension-id CDATA #REQUIRED \ No newline at end of file Modified: lucene/nutch/trunk/conf/parse-plugins.xml URL: http://svn.apache.org/viewcvs/lucene/nutch/trunk/conf/parse-plugins.xml?rev=379403r1=379402r2=379403view=diff == --- lucene/nutch/trunk/conf/parse-plugins.xml (original) +++ lucene/nutch/trunk/conf/parse-plugins.xml Tue Feb 21 01:54:21 2006 @@ -218,4 +218,33 @@ plugin id=parse-ext / /mimeType + !-- alias mappings for parse-xxx names to the actual extension implementation + ids described in each plugin's plugin.xml file -- + aliases + alias name=parse-ext extension-id=ExtParser / + alias name=parse-html + extension-id=org.apache.nutch.parse.html.HtmlParser / + alias name=parse-js extension-id=JSParser / + alias name=parse-mp3 + extension-id=org.apache.nutch.parse.mp3.MP3Parser / + alias name=parse-msexcel + extension-id=org.apache.nutch.parse.msexcel.MSExcelParser / + alias name=parse-mspowerpoint + extension-id=org.apache.nutch.parse.mspowerpoint.MSPowerPointParser / + alias name=parse-msword + extension-id=org.apache.nutch.parse.msword.MSWordParser / + alias name=parse-pdf + extension-id=org.apache.nutch.parse.pdf.PdfParser / + alias name=parse-rss + extension-id=org.apache.nutch.parse.rss.RSSParser / + alias name=parse-rtf + extension-id=org.apache.nutch.parse.rtf.RTFParseFactory / + alias name=parse-swf + extension-id=org.apache.nutch.parse.swf.SWFParser / + alias name=parse-text + extension-id=org.apache.nutch.parse.text.TextParser / + alias name=parse-zip + extension-id=org.apache.nutch.parse.zip.ZipParser / + /aliases + /parse-plugins
svn commit: r379419 - in /lucene/nutch/trunk: site/mailing_lists.html site/mailing_lists.pdf src/site/src/documentation/content/xdocs/mailing_lists.xml
Author: jerome
Date: Tue Feb 21 03:10:42 2006
New Revision: 379419
URL: http://svn.apache.org/viewcvs?rev=379419view=rev
Log:
NUTCH-214, Add a search mailing list archive link (Jake Vanderdray)
Modified:
lucene/nutch/trunk/site/mailing_lists.html
lucene/nutch/trunk/site/mailing_lists.pdf
lucene/nutch/trunk/src/site/src/documentation/content/xdocs/mailing_lists.xml
Modified: lucene/nutch/trunk/site/mailing_lists.html
URL:
http://svn.apache.org/viewcvs/lucene/nutch/trunk/site/mailing_lists.html?rev=379419r1=379418r2=379419view=diff
==
--- lucene/nutch/trunk/site/mailing_lists.html (original)
+++ lucene/nutch/trunk/site/mailing_lists.html Tue Feb 21 03:10:42 2006
@@ -3,7 +3,7 @@
head
META http-equiv=Content-Type content=text/html; charset=UTF-8
meta content=Apache Forrest name=Generator
-meta name=Forrest-version content=0.6
+meta name=Forrest-version content=0.7
meta name=Forrest-skin-name content=pelt
titleNutch Mailing Lists/title
link type=text/css href=skin/basic.css rel=stylesheet
@@ -16,49 +16,22 @@
body onload=init()
script type=text/javascriptndeSetTextSize();/script
div id=top
-!--+
-|breadtrail
-+--
div class=breadtrail
a href=http://www.apache.org/;Apache/a gt; a
href=http://lucene.apache.org/;Lucene/a gt; a
href=http://lucene.apache.org/nutch/;Nutch/ascript
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=http://lucene.apache.org/java/docs/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/nutch/;img class=logoImage alt=Nutch
src=images/nutch-logo.gif title=Open Source Web Search Software/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=hiddeninput
onFocus=getBlank (this, 'Search the site with google:'); value=Search the
site with google: size=25 name=q id=query type=textnbsp;
-input name=Search value=Search type=submit
+input value=lucene.apache.org name=sitesearch type=hiddeninput
onFocus=getBlank (this, 'Search the site with google'); size=25 name=q
id=query type=text value=Search the site with googlenbsp;
+input attr=value name=Search value=Search
type=submit
/form
/div
-!--+
-|end search
-+--
-!--+
-|start Tabs
-+--
ul id=tabs
li class=current
a class=base-selected href=index.htmlMain/a
@@ -67,110 +40,83 @@
a class=base-not-selected href=http://wiki.apache.org/nutch/;Wiki/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 language=JavaScript!--
- document.write(Published: + document.lastModified);
- // --/script
-/div
-!--+
-|breadtrail
-+--
+script type=text/javascript!--
+document.write(textLast Published:/text + document.lastModified);
+// --/script
+/div
div class=breadtrail
nbsp;
/div
-!--+
-|start Menu, mainarea
-+--
-!--+
-|start Menu
-+--
div id=menu
div onclick=SwitchMenu('menu_1.1', 'skin/') id=menu_1.1Title
class=menutitleProject/div
div id=menu_1.1 class=menuitemgroup
div class=menuitem
-a title= href=index.htmlNews/a
+a href=index.htmlNews/a
/div
div class=menuitem
-a title= href=about.htmlAbout/a
+a href=about.htmlAbout/a
/div
div class=menuitem
-a title= href=credits.htmlCredits/a
+a href=credits.htmlCredits/a
/div
div class=menuitem
-a title= href=http://www.cafepress.com/nutch/;Buy Stuff/a
+a href=http://www.cafepress.com/nutch/;Buy Stuff/a
/div
/div
div onclick=SwitchMenu('menu_1.2', 'skin/') id=menu_1.2Title
class=menutitleDocumentation/div
div id=menu_1.2 class=menuitemgroup
div class=menuitem
-a title= href=http://wiki.apache.org/nutch/FAQ;FAQ/a
+a href=http://wiki.apache.org/nutch/FAQ;FAQ/a
/div
div class=menuitem
-a title= href=http://wiki.apache.org/nutch/;Wiki/a
+a href=http://wiki.apache.org/nutch/;Wiki/a
/div
div class=menuitem
-a title= href=tutorial.htmlTutorial/a
+a href=tutorial.htmlTutorial/a
/div
div class=menuitem
-a title= href=bot.htmlRobot /a
+a href=bot.htmlRobot /a
/div
div class=menuitem
-a title= href=i18n.htmli18n/a
+a href=i18n.htmli18n/a
/div
div class=menuitem
-a title= href=apidocs/index.htmlAPI Docs/a
+a href=apidocs/index.htmlAPI Docs/a
/div
/div
div onclick=SwitchMenu('menu_selected_1.3', 'skin/')
id=menu_selected_1.3Title class=menutitle style=background-image:
[Nutch Wiki] Update of Website Update HOWTO by JakeVanderdray
Dear Wiki user,
You have subscribed to a wiki page or wiki category on Nutch Wiki for change
notification.
The following page has been changed by JakeVanderdray:
http://wiki.apache.org/nutch/Website_Update_HOWTO
--
-
- ''This page is prepared for Nutch committers. You need committer rights to
modify Nutch Website.''
-
== What you need ==
[http://forrest.apache.org Apache Forrest] - Publishing framework used for
Nutch Website maintenance.
@@ -14, +11 @@
1. Run {{{forrest}}} to build current version of documentation. If the
build was successful it means Forrest was correctly installed and generated
site is in {{{src/site/build/site}}} directory.
1. Modify files in {{{src/site/src}}} (mainly in
{{{src/site/src/documentation/content/xdocs}}}). Run {{{forrest}}} in
{{{/src/site}}} and review the changes after build.
+ If you aren't a committer for this project, you now need to follow the
instruction in HowToContribute to get your changes updated on the site. If you
are a committer, it's time to deploy the site.
+
== How to deploy the site ==
1. When you are finally happy with your changes copy files from
{{{src/site/build/site}}} directory to {{{site}}} and commit them to SVN.
[Nutch Wiki] Update of Website Update HOWTO by JakeVanderdray
Dear Wiki user,
You have subscribed to a wiki page or wiki category on Nutch Wiki for change
notification.
The following page has been changed by JakeVanderdray:
http://wiki.apache.org/nutch/Website_Update_HOWTO
--
1. Run {{{forrest}}} to build current version of documentation. If the
build was successful it means Forrest was correctly installed and generated
site is in {{{src/site/build/site}}} directory.
1. Modify files in {{{src/site/src}}} (mainly in
{{{src/site/src/documentation/content/xdocs}}}). Run {{{forrest}}} in
{{{/src/site}}} and review the changes after build.
- If you aren't a committer for this project, you now need to follow the
instruction in HowToContribute to get your changes updated on the site. If you
are a committer, it's time to deploy the site.
+ If you aren't a committer for this project, you now need to follow the
instructions in HowToContribute to get your changes applied to the site.
You'll specifically want to read the sections on Creating a patch and
Proposing your work. If you are a committer, it's time to deploy the site.
== How to deploy the site ==
svn commit: r379511 - in /lucene/nutch/trunk: docs/fr/help.html src/web/pages/fr/help.xml
Author: jerome
Date: Tue Feb 21 08:05:07 2006
New Revision: 379511
URL: http://svn.apache.org/viewcvs?rev=379511view=rev
Log:
Add fr help page
Added:
lucene/nutch/trunk/docs/fr/help.html (with props)
lucene/nutch/trunk/src/web/pages/fr/help.xml (with props)
Added: lucene/nutch/trunk/docs/fr/help.html
URL:
http://svn.apache.org/viewcvs/lucene/nutch/trunk/docs/fr/help.html?rev=379511view=auto
==
--- lucene/nutch/trunk/docs/fr/help.html (added)
+++ lucene/nutch/trunk/docs/fr/help.html Tue Feb 21 08:05:07 2006
@@ -0,0 +1,161 @@
+!DOCTYPE HTML PUBLIC -//W3C//DTD HTML 4.01 Transitional//EN
+html!--This page is automatically generated. Do not edit!--
+head
+META http-equiv=Content-Type content=text/html; charset=UTF-8
+titleNutch: aide/title
+style type=text/css
+.menuTd {background-color: #F9F7F4; height: 25; onMouseOver:
this.style.backgroundColor='#ECE5DC';}
+.menuTdhover {background-color: #ECE5DC; height: 25; onMouseOver:
this.style.backgroundColor='#ECE5DC';}
+.menuEntry { font-family: Arial, Helvetica, sans-serif; font-size: 12px;
color: #00; text-decoration: none}
+.body {background-color: #F9F7F4;}
+.bodytext { font-family: Arial, Helvetica, sans-serif; font-size: 12px;
color: #00; text-decoration: none}
+.title { font-family: Arial, Helvetica, sans-serif; font-size: 26px; color:
#FF9900; text-decoration: none}
+.intro { font-family: Arial, Helvetica, sans-serif; font-size: 12px; color:
#FF9900; text-decoration: none}
+.orangeTd {background-color: #FF9900}
+ul {list-style-image: url(../img/reiter/ul.gif)}
+h3 {font-family: Arial, Helvetica, sans-serif; font-size: 16px; color:
#00;}
+h4 {font-family: Arial, Helvetica, sans-serif; font-size: 14px; color:
#00;}
+.url {color: #996600;}
+.highlight {font-weight: bold;}
+.ellipsis {font-weight: bold;}
+/style
+link type=image/x-icon href=../img/favicon.ico rel=icon
+link type=image/x-icon href=../img/favicon.ico rel=shortcut icon
+script type=text/javascript
+!--
+function queryfocus() { document.search.query.focus(); }
+// --/script
+/head
+body onLoad=queryfocus();
+!--This file is automatically generated. Do not edit!--
+table cellspacing=0 cellpadding=0 border=0 width=635
+tr
+td rowspan=2 width=140 valign=bottoma href=./img border=0
src=../img/reiter/logo_nutch.gif/aimg height=1 width=140
src=../img/reiter/spacer_66.gif/td
+/tr
+tr
+td align=right valign=bottom width=495
+table width=495 cellspacing=0 cellpadding=0 border=0
+tr
+td width=400 background=../img/reiter/_bg_reiter.gifnbsp;/tdtd
width=10 valign=bottom height=28img border=0
src=../img/reiter/reiter_inactive_le1.gif/tdtd nowrap=nowrap
valign=bottom background=../img/reiter/_bg_reiter_inactive.gifa
href=about.html class=bodytextA propos/a/tdtd width=10
valign=bottom height=28img border=0
src=../img/reiter/reiter_inactive_ri.gif/tdtd width=10 valign=bottom
height=28img border=0 src=../img/reiter/reiter_inactive_le.gif/tdtd
nowrap=nowrap valign=bottom
background=../img/reiter/_bg_reiter_inactive.gifa
href=http://wiki.apache.org/nutch/FAQ; class=bodytextQuestions
freacute;quentes/a/tdtd width=10 valign=bottom height=28img
border=0 src=../img/reiter/reiter_inactive_ri.gif/td
+/tr
+/table
+/td
+/tr
+/table
+table cellspacing=0 cellpadding=0 border=0 width=635
+tr valign=top
+td width=140
+table cellspacing=0 cellpadding=0 width=100%
+tr
+td#160;/td
+/tr
+/table
+/tdtd background=../img/reiter/_spacer_cc.gif
width=20#160;/tdtd class=body width=475
+table cellspacing=0 cellpadding=0 border=0 width=475
+tr
+td valign=bottom width=275 height=125 class=titleaide/tdtd
valign=bottom width=200 height=125img
src=../img/reiter/robots.gif/td
+/tr
+/table
+br class=br
+span class=bodytext
+
+/spanspan class=bodytext
+h3Requecirc;tes/h3
+/spanspan class=bodytext
+Pour effectuer une recherche avec Nutch, il suffit de saisir quelques mots.
+/spanspan class=bodytext
+ul
+
+liLes reacute;sultats contiendront uniquement les pages qui contiennent
+span style=font-style: italic;tous/span les mots de la question./li
+
+liUtilisez les doubles chevrons autour des termes qui doivent ecirc;tre
adjacents,
+comme dans le cas d'une phrase. Par exemple span style=font-weight: bold;
+Nouvelle Zeacute;lande/span./li
+
+liLa ponctuation entre les mots est ignoreacute;e. Ainsi, la recherche
+span style=font-weight: bold;http://www.nutch.org//span est
eacute;quivalente agrave;
+span style=font-weight: bold;http www nutch org/span./li
+
+liLa recherche n'est pas sensible agrave; la casse. Ainsi, la recherche
+span style=font-weight: bold;NuTcH/span est eacute;quivalente agrave;
span style=font-weight: bold;nUtCh/span./li
+
+liVous pouvez exclure un mot des reacute;sultats en placcedil;ant un signe
moins
+devant. Ainsi, la recherche span style=font-weight: bold;football
+-nfl/span retournera les pages qui parlent de football, mais qui ne
contiennent
+pas le mot nfl./li
+
+/ul
