lee/heritrix3
1
0 Fork 0
mirror of https://github.com/internetarchive/heritrix3.git synced 2026-11-09 23:43:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix issues revealed in extra tests

Browse Source 
* H1toH3.map, migrate-template-crawler-beans.cxml, .classpath
    move resources to 'resources' src subdirectory, so included in built JAR
    move 'resources' directorys to library rather than source directories for dev-time reachability
* MigrateH1to3Tool.java
    handle H1 values that just need capitalization
    report all 'no rule' situations as 'needs attention' 
    touchup explanations and comments
    enable uriCanonicalizationRule overrides
This commit is contained in:
gojomo committed 2009-10-07 10:24:05 +00:00
1 parent f114448e6f
commit 64a79ea9e6
4 files changed
+42 -32
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

engine/src/main/java/org/archive/crawler/migrate/H1toH3.map
-121
View File
@@ -1,121 +0,0 @@
metadata.jobName|//meta/name|default
metadata.description|//meta/description|Default Profile
metadata.operator|//meta/operator|Admin
$|//meta/date|20091006215050
$|//controller/*[@name="settings-directory"]|settings
loggerModule.path|//controller/*[@name="logs-path"]|logs
crawlController.checkpointsDir|//controller/*[@name="checkpoints-path"]|checkpoints
bdb.dir|//controller/*[@name="state-path"]|state
crawlController.scratchDir|//controller/*[@name="scratch-path"]|scratch
crawlLimiter.maxBytesDownload|//controller/*[@name="max-bytes-download"]|0
crawlLimiter.maxDocumentsDownload|//controller/*[@name="max-document-download"]|0
crawlLimiter.maxTimeSeconds|//controller/*[@name="max-time-sec"]|0
crawlController.maxToeThreads|//controller/*[@name="max-toe-threads"]|50
crawlController.recorderOutBufferBytes|//controller/*[@name="recorder-out-buffer-bytes"]|4096
crawlController.recorderInBufferBytes|//controller/*[@name="recorder-in-buffer-bytes"]|65536
bdb.cachePercent|//controller/*[@name="bdb-cache-percent"]|0
$|//controller/*[@name="scope"]/*[@name="enabled"]|true
seeds.textSource.path|//controller/*[@name="scope"]/*[@name="seedsfile"]|seeds.txt
$|//controller/*[@name="scope"]/*[@name="reread-seeds-on-config"]|true
scope.rules[1].decision|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="acceptIfSurtPrefixed"]/*[@name="decision"]|ACCEPT
scope.rules[1].seedsAsSurtPrefixes|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="acceptIfSurtPrefixed"]/*[@name="seeds-as-surt-prefixes"]|true
scope.rules[1].alsoCheckVia|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="acceptIfSurtPrefixed"]/*[@name="also-check-via"]|false
$na|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="acceptIfSurtPrefixed"]/*[@name="rebuild-on-reconfig"]|true
scope.rules[2].maxHops|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="rejectIfTooManyHops"]/*[@name="max-hops"]|20
scope.rules[3].maxTransHops|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="acceptIfTranscluded"]/*[@name="max-trans-hops"]|3
scope.rules[3].maxSpeculativeHops|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="acceptIfTranscluded"]/*[@name="max-speculative-hops"]|1
scope.rules[6].maxRepetitions|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="rejectIfPathological"]/*[@name="max-repetitions"]|2
scope.rules[7].maxPathDepth|//controller/*[@name="scope"]/*[@name="decide-rules"]/*[@name="rules"]/*[@name="rejectIfTooManyPathSegs"]/*[@name="max-path-depth"]|20
*metadata.userAgentTemplate|//controller/*[@name="http-headers"]/*[@name="user-agent"]|Mozilla/5.0|(compatible;|heritrix/@VERSION@|+PROJECT_URL_HERE)
metadata.operatorFrom|//controller/*[@name="http-headers"]/*[@name="from"]|CONTACT_EMAIL_ADDRESS_HERE
*metadata.robotsHonoringPolicy.type|//controller/*[@name="robots-honoring-policy"]/*[@name="type"]|classic
metadata.robotsHonoringPolicy.masquerade|//controller/*[@name="robots-honoring-policy"]/*[@name="masquerade"]|false
disposition.delayFactor|//controller/*[@name="frontier"]/*[@name="delay-factor"]|4.0
disposition.maxDelayMs|//controller/*[@name="frontier"]/*[@name="max-delay-ms"]|20000
disposition.minDelayMs|//controller/*[@name="frontier"]/*[@name="min-delay-ms"]|2000
disposition.respectCrawlDelayUpToSeconds|//controller/*[@name="frontier"]/*[@name="respect-crawl-delay-up-to-secs"]|300
frontier.maxRetries|//controller/*[@name="frontier"]/*[@name="max-retries"]|30
frontier.retryDelaySeconds|//controller/*[@name="frontier"]/*[@name="retry-delay-seconds"]|900
preparer.preferenceEmbedHops|//controller/*[@name="frontier"]/*[@name="preference-embed-hops"]|1
$|//controller/*[@name="frontier"]/*[@name="total-bandwidth-usage-KB-sec"]|0
disposition.maxPerHostBandwidthUsageKbSec|//controller/*[@name="frontier"]/*[@name="max-per-host-bandwidth-usage-KB-sec"]|0
*preparer.queueAssignmentPolicy|//controller/*[@name="frontier"]/*[@name="queue-assignment-policy"]|org.archive.crawler.frontier.HostnameQueueAssignmentPolicy
crawlController.pauseAtStart|//controller/*[@name="frontier"]/*[@name="pause-at-start"]|false
crawlController.pauseAtFinish|//controller/*[@name="frontier"]/*[@name="pause-at-finish"]|false
seeds.sourceTagSeeds|//controller/*[@name="frontier"]/*[@name="source-tag-seeds"]|false
frontier.recoveryLogEnabled|//controller/*[@name="frontier"]/*[@name="recovery-log-enabled"]|true
frontier.holdQueues|//controller/*[@name="frontier"]/*[@name="hold-queues"]|true
frontier.balanceReplenishAmount|//controller/*[@name="frontier"]/*[@name="balance-replenish-amount"]|3000
frontier.errorPenaltyAmount|//controller/*[@name="frontier"]/*[@name="error-penalty-amount"]|100
frontier.queueTotalBudget|//controller/*[@name="frontier"]/*[@name="queue-total-budget"]|-1
*preparer.costAssignmentPolicy|//controller/*[@name="frontier"]/*[@name="cost-policy"]|org.archive.crawler.frontier.ZeroCostAssignmentPolicy
frontier.snoozeLongMs|//controller/*[@name="frontier"]/*[@name="snooze-deactivate-ms"]|300000
$|//controller/*[@name="frontier"]/*[@name="target-ready-backlog"]|50
*frontier.uriUniqFilter|//controller/*[@name="frontier"]/*[@name="uri-included-structure"]|org.archive.crawler.util.BdbUriUniqFilter
frontier.dumpPendingAtClose|//controller/*[@name="frontier"]/*[@name="dump-pending-at-close"]|false
$|//controller/*[@name="uri-canonicalization-rules"]/*[@name="Lowercase"]/*[@name="enabled"]|true
$|//controller/*[@name="uri-canonicalization-rules"]/*[@name="Userinfo"]/*[@name="enabled"]|true
$|//controller/*[@name="uri-canonicalization-rules"]/*[@name="WWW[0-9]*"]/*[@name="enabled"]|true
$|//controller/*[@name="uri-canonicalization-rules"]/*[@name="SessionIDs"]/*[@name="enabled"]|true
$|//controller/*[@name="uri-canonicalization-rules"]/*[@name="SessionCFIDs"]/*[@name="enabled"]|true
$|//controller/*[@name="uri-canonicalization-rules"]/*[@name="QueryStrPrefix"]/*[@name="enabled"]|true
preselector.enabled|//controller/*[@name="pre-fetch-processors"]/*[@name="Preselector"]/*[@name="enabled"]|true
preselector.logToFile|//controller/*[@name="pre-fetch-processors"]/*[@name="Preselector"]/*[@name="override-logger"]|false
preselector.recheckScope|//controller/*[@name="pre-fetch-processors"]/*[@name="Preselector"]/*[@name="recheck-scope"]|true
preselector.blockAll|//controller/*[@name="pre-fetch-processors"]/*[@name="Preselector"]/*[@name="block-all"]|false
preconditions.enabled|//controller/*[@name="pre-fetch-processors"]/*[@name="Preprocessor"]/*[@name="enabled"]|true
preconditions.ipValidityDurationSeconds|//controller/*[@name="pre-fetch-processors"]/*[@name="Preprocessor"]/*[@name="ip-validity-duration-seconds"]|21600
preconditions.robotsValidityDurationSeconds|//controller/*[@name="pre-fetch-processors"]/*[@name="Preprocessor"]/*[@name="robot-validity-duration-seconds"]|86400
preconditions.calculateRobotsOnly|//controller/*[@name="pre-fetch-processors"]/*[@name="Preprocessor"]/*[@name="calculate-robots-only"]|false
fetchDns.enabled|//controller/*[@name="fetch-processors"]/*[@name="DNS"]/*[@name="enabled"]|true
fetchDns.acceptNonDnsResolves|//controller/*[@name="fetch-processors"]/*[@name="DNS"]/*[@name="accept-non-dns-resolves"]|false
fetchDns.digestContent|//controller/*[@name="fetch-processors"]/*[@name="DNS"]/*[@name="digest-content"]|true
fetchDns.digestAlgorithm|//controller/*[@name="fetch-processors"]/*[@name="DNS"]/*[@name="digest-algorithm"]|sha1
fetchHttp.enabled|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="enabled"]|true
fetchHttp.timeoutSeconds|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="timeout-seconds"]|1200
fetchHttp.soTimeoutMs|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="sotimeout-ms"]|20000
fetchHttp.maxFetchKBSec|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="fetch-bandwidth"]|0
fetchHttp.maxLengthBytes|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="max-length-bytes"]|0
fetchHttp.ignoreCookies|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="ignore-cookies"]|false
$|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="use-bdb-for-cookies"]|true
*fetchHttp.sslTrustLevel|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="trust-level"]|open
fetchHttp.defaultEncoding|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="default-encoding"]|ISO-8859-1
fetchHttp.digestContent|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="digest-content"]|true
fetchHttp.digestAlgorithm|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="digest-algorithm"]|sha1
fetchHttp.sendIfModifiedSince|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="send-if-modified-since"]|true
fetchHttp.sendIfNoneMatch|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="send-if-none-match"]|true
fetchHttp.sendConnectionClose|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="send-connection-close"]|true
fetchHttp.sendReferer|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="send-referer"]|true
fetchHttp.sendRange|//controller/*[@name="fetch-processors"]/*[@name="HTTP"]/*[@name="send-range"]|false
extractorHttp.enabled|//controller/*[@name="extract-processors"]/*[@name="ExtractorHTTP"]/*[@name="enabled"]|true
extractorHtml.enabled|//controller/*[@name="extract-processors"]/*[@name="ExtractorHTML"]/*[@name="enabled"]|true
extractorHtml.extractJavascript|//controller/*[@name="extract-processors"]/*[@name="ExtractorHTML"]/*[@name="extract-javascript"]|true
extractorHtml.treatFramesAsEmbedLinks|//controller/*[@name="extract-processors"]/*[@name="ExtractorHTML"]/*[@name="treat-frames-as-embed-links"]|true
extractorHtml.ignoreFormActionUrls|//controller/*[@name="extract-processors"]/*[@name="ExtractorHTML"]/*[@name="ignore-form-action-urls"]|false
extractorHtml.extractOnlyFormGets|//controller/*[@name="extract-processors"]/*[@name="ExtractorHTML"]/*[@name="extract-only-form-gets"]|true
extractorHtml.extractValueAttributes|//controller/*[@name="extract-processors"]/*[@name="ExtractorHTML"]/*[@name="extract-value-attributes"]|true
extractorHtml.ignoreUnexpectedHtml|//controller/*[@name="extract-processors"]/*[@name="ExtractorHTML"]/*[@name="ignore-unexpected-html"]|true
extractorCss.enabled|//controller/*[@name="extract-processors"]/*[@name="ExtractorCSS"]/*[@name="enabled"]|true
extractorJs.enabled|//controller/*[@name="extract-processors"]/*[@name="ExtractorJS"]/*[@name="enabled"]|true
extractorSwf.enabled|//controller/*[@name="extract-processors"]/*[@name="ExtractorSWF"]/*[@name="enabled"]|true
arcWriter.enabled|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="enabled"]|true
arcWriter.compress|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="compress"]|true
arcWriter.prefix|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="prefix"]|IAH
arcWriter.suffix|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="suffix"]|${HOSTNAME}
arcWriter.maxFileSizeBytes|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="max-size-bytes"]|100000000
*arcWriter.storePaths[0]|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="path"]/string|arcs
arcWriter.poolMaxActive|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="pool-max-active"]|5
arcWriter.poolMaxWaitMs|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="pool-max-wait"]|300000
arcWriter.maxTotalBytesToWrite|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="total-bytes-to-write"]|0
arcWriter.skipIdenticalDigests|//controller/*[@name="write-processors"]/*[@name="Archiver"]/*[@name="skip-identical-digests"]|false
$|//controller/*[@name="post-processors"]/*[@name="Updater"]/*[@name="enabled"]|true
$|//controller/*[@name="post-processors"]/*[@name="LinksScoper"]/*[@name="enabled"]|true
$|//controller/*[@name="post-processors"]/*[@name="LinksScoper"]/*[@name="override-logger"]|false
candidates.seedsRedirectNewSeeds|//controller/*[@name="post-processors"]/*[@name="LinksScoper"]/*[@name="seed-redirects-new-seed"]|true
preparer.preferenceDepthHops|//controller/*[@name="post-processors"]/*[@name="LinksScoper"]/*[@name="preference-depth-hops"]|-1
$|//controller/*[@name="post-processors"]/*[@name="Scheduler"]/*[@name="enabled"]|true
statisticsTracker.intervalSeconds|//controller/*[@name="loggers"]/*[@name="crawl-statistics"]/*[@name="interval-seconds"]|20
bdb.checkpointCopyLogs|//controller/*[@name="checkpoint-copy-bdbje-logs"]|true
$|//controller/*[@name="recover-retain-failures"]|false
$|//controller/*[@name="recover-scope-includes"]|true
$|//controller/*[@name="recover-scope-enqueues"]|true
engine/src/main/java/org/archive/crawler/migrate/MigrateH1to3Tool.java
+29 -19
View File
@@ -76,8 +76,6 @@ public class MigrateH1to3Tool {
return;
}
File sourceOrderXmlFile = new File(args[0]);
File destinationH3JobDir = new File(args[1]);
@@ -89,7 +87,7 @@ public class MigrateH1to3Tool {
System.out.print("Migrating settings...");
InputStream inStream = getClass().getResourceAsStream(
"migrate-template-crawler-beans.cxml");
"/org/archive/crawler/migrate/migrate-template-crawler-beans.cxml");
String template = IOUtils.toString(inStream);
inStream.close();
@@ -105,11 +103,18 @@ public class MigrateH1to3Tool {
for(String key : h1simpleSettings.keySet()) {
String beanPath = migrateH1toH3Map.get(key);
String value = h1simpleSettings.get(key);
System.out.print(".");
if(beanPath==null) {
System.err.println("no rule found for: "+key);
} else if (beanPath.startsWith("$")) {
notApplicable.add(key+" "+value);
} else if (beanPath.startsWith("*")) {
// no equivalence rule
needsAttention.add(key+" "+value);
continue;
}
if (beanPath.startsWith("$")) {
// rule indicates not-available/not-applicable
notApplicable.add(key+" "+value);
continue;
}
if (beanPath.startsWith("*")) {
// TODO: needs special handling
if(beanPath.equals("*metadata.userAgentTemplate")) {
splitH1userAgent(value,sb);
@@ -117,16 +122,19 @@ public class MigrateH1to3Tool {
} else {
needsAttention.add(key+" "+value);
}
} else {
sb
.append(beanPath)
.append("=")
.append(value)
.append("\n");
migrated++;
continue;
}
if (beanPath.startsWith("^")) {
// uppercase to new enum-style
value = value.toUpperCase();
beanPath = beanPath.substring(1);
}
System.out.print(".");
sb
.append(beanPath)
.append("=")
.append(value)
.append("\n");
migrated++;
}
System.out.println();
System.out.println();
@@ -144,12 +152,12 @@ public class MigrateH1to3Tool {
System.out.println(notApplicable.size()+" settings skipped as not-applicable");
System.out.println("These are probably harmless, but if the following settings were");
System.out.println("important to your crawl, investigate other options.");
System.out.println("important to your crawl process, investigate other options.");
listProblems(notApplicable);
System.out.println();
System.out.println(needsAttention.size()+" settings may need attention");
System.out.println("Please review your original crawl and the created H3 job, for each");
System.out.println("of the following and update manually to reflect your intent ");
System.out.println("of the following, and manually update as needed.");
listProblems(needsAttention);
System.out.println();
System.out.println(migrated +" H1 settings successfully migrated to H3 configuration");
@@ -178,6 +186,7 @@ public class MigrateH1to3Tool {
"^.*?\\+(http://[^)]*).*$",
"$1");
String newTemplate = userAgent.replace(originalUrl,"@OPERATOR_CONTACT_URL@");
// TODO: catch, change outdated version info?
sb
.append("metadata.operatorContactUrl=")
.append(originalUrl)
@@ -189,7 +198,8 @@ public class MigrateH1to3Tool {
protected Map<String, String> getMigrateMap() throws IOException {
Map<String,String> map = new HashMap<String,String>();
InputStream inStream = getClass().getResourceAsStream("H1toH3.map");
InputStream inStream = getClass().getResourceAsStream(
"/org/archive/crawler/migrate/H1toH3.map");
LineIterator iter = IOUtils.lineIterator(inStream, "UTF-8");
while(iter.hasNext()) {
String[] fields = iter.nextLine().split("\\|");
engine/src/main/java/org/archive/crawler/migrate/migrate-template-crawler-beans.cxml
-511
View File
@@ -1,511 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<!--
HERITRIX 3 CRAWL JOB CONFIGURATION FILE - MIGRATE TEMPLATE
This is a relatively minimal configuration suitable for many crawls.
Commented-out beans and properties are provided as an example; values
shown in comments reflect the actual defaults which are in effect
without specification. (To change from the default behavior,
uncomment AND alter the shown values.)
-->
<beans xmlns="http://www.springframework.org/schema/beans"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:context="http://www.springframework.org/schema/context"
xmlns:aop="http://www.springframework.org/schema/aop"
xmlns:tx="http://www.springframework.org/schema/tx"
xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-2.0.xsd
http://www.springframework.org/schema/aop http://www.springframework.org/schema/aop/spring-aop-2.0.xsd
http://www.springframework.org/schema/tx http://www.springframework.org/schema/tx/spring-tx-2.0.xsd
http://www.springframework.org/schema/context http://www.springframework.org/schema/context/spring-context-2.5.xsd">
<context:annotation-config/>
<!--
OVERRIDES
Values elsewhere in the configuration may be replaced ('overridden')
by a Properties map declared in a PropertiesOverrideConfigurer,
using a dotted-bean-path to address individual bean properties.
This allows us to collect a few of the most-often changed values
in an easy-to-edit format here at the beginning of the model
configuration.
-->
<!-- overrides from a text property list -->
<bean id="simpleOverrides" class="org.springframework.beans.factory.config.PropertyOverrideConfigurer">
<property name="properties">
<value>
# This Properties map is specified in the Java 'property list' text format
# http://java.sun.com/javase/6/docs/api/java/util/Properties.html#load%28java.io.Reader%29
###MIGRATE_OVERRIDES###
</value>
</property>
</bean>
<!-- overrides from declared <prop> elements, more easily allowing
multiline values or even declared beans -->
<bean id="longerOverrides" class="org.springframework.beans.factory.config.PropertyOverrideConfigurer">
<property name="properties">
<props>
</props>
</property>
</bean>
<!-- CRAWL METADATA: including identification of crawler/operator -->
<bean id="metadata" class="org.archive.modules.CrawlMetadata" autowire="byName">
<property name="operatorContactUrl" value="[see override above]"/>
<property name="jobName" value="[see override above]"/>
<property name="description" value="[see override above]"/>
<!-- <property name="operator" value=""/> -->
<!-- <property name="operatorFrom" value=""/> -->
<!-- <property name="organization" value=""/> -->
<!-- <property name="audience" value=""/> -->
<!-- <property name="userAgentTemplate"
value="Mozilla/5.0 (compatible; heritrix/@VERSION@ +@OPERATOR_CONTACT_URL@)"/> -->
</bean>
<!-- SEEDS: crawl starting points -->
<!-- ConfigFile approach: specifying external seeds.txt file -->
<bean id="seeds" class="org.archive.modules.seeds.TextSeedModule">
<property name="textSource">
<bean class="org.archive.spring.ConfigFile">
<property name="path" value="seeds.txt" />
</bean>
</property>
<!-- <property name='sourceTagSeeds' value='false'/> -->
</bean>
<!-- SEEDS ALTERNATE APPROACH:
ConfigString allows simple, inline specification of a moderate
number of seeds; see below comment for example of using an
arbitrarily-large external file.
Use either the above, or this, but not both. -->
<!--
<bean id="seeds" class="org.archive.modules.seeds.TextSeedModule">
<property name="textSource">
<bean class="org.archive.spring.ConfigString">
<property name="value">
<value>
# [see override above]
</value>
</property>
</bean>
</property>
<property name='sourceTagSeeds' value='false'/>
</bean>
-->
<!-- SCOPE: rules for which discovered URIs to crawl; order is very
important because last decision returned other than 'NONE' wins. -->
<bean id="scope" class="org.archive.modules.deciderules.DecideRuleSequence">
<property name="rules">
<list>
<!-- Begin by REJECTing all... -->
<bean class="org.archive.modules.deciderules.RejectDecideRule">
</bean>
<!-- ...then ACCEPT those within configured/seed-implied SURT prefixes... -->
<bean class="org.archive.modules.deciderules.surt.SurtPrefixedDecideRule">
<!-- <property name="seedsAsSurtPrefixes" value="true" /> -->
<!-- <property name="alsoCheckVia" value="true" /> -->
<!-- <property name="surtsSourceFile" value="" /> -->
<!-- <property name="surtsDumpFile" value="surts.dump" /> -->
</bean>
<!-- ...but REJECT those more than a configured link-hop-count from start... -->
<bean class="org.archive.modules.deciderules.TooManyHopsDecideRule">
<!-- <property name="maxHops" value="20" /> -->
</bean>
<!-- ...but ACCEPT those more than a configured link-hop-count from start... -->
<bean class="org.archive.modules.deciderules.TransclusionDecideRule">
<!-- <property name="maxTransHops" value="2" /> -->
<!-- <property name="maxSpeculativeHops" value="1" /> -->
</bean>
<!-- ...but REJECT those from a configurable (initially empty) set of REJECT SURTs... -->
<bean class="org.archive.modules.deciderules.surt.SurtPrefixedDecideRule">
<property name="decision" value="REJECT"/>
<property name="seedsAsSurtPrefixes" value="false"/>
<property name="surtsDumpFile" value="negative-surts.dump" />
<!-- <property name="surtsSourceFile" value="" /> -->
</bean>
<!-- ...and REJECT those from a configurable (initially empty) set of URI regexes... -->
<bean class="org.archive.modules.deciderules.MatchesListRegexDecideRule">
<!-- <property name="listLogicalOr" value="true" /> -->
<!-- <property name="regexList">
<list>
</list>
</property> -->
</bean>
<!-- ...and REJECT those with suspicious repeating path-segments... -->
<bean class="org.archive.modules.deciderules.PathologicalPathDecideRule">
<!-- <property name="maxRepetitions" value="2" /> -->
</bean>
<!-- ...and REJECT those with more than threshold number of path-segments... -->
<bean class="org.archive.modules.deciderules.TooManyPathSegmentsDecideRule">
<!-- <property name="maxPathDepth" value="20" /> -->
</bean>
<!-- ...but always ACCEPT those marked as prerequisitee for another URI... -->
<bean class="org.archive.modules.deciderules.PrerequisiteAcceptDecideRule">
</bean>
</list>
</property>
</bean>
<!--
PROCESSING CHAINS
Much of the crawler's work is specified by the sequential
application of swappable Processor modules. These Processors
are collected into three 'chains. The CandidateChain is applied
to URIs being considered for inclusion, before a URI is enqueued
for collection. The FetchChain is applied to URIs when their
turn for collection comes up. The DispositionChain is applied
after a URI is fetched and analyzed/link-extracted.
-->
<!-- CANDIDATE CHAIN -->
<!-- processors declared as named beans -->
<bean id="candidateScoper" class="org.archive.crawler.prefetch.CandidateScoper">
</bean>
<bean id="preparer" class="org.archive.crawler.prefetch.FrontierPreparer">
<!-- <property name="preferenceDepthHops" value="-1" /> -->
<!-- <property name="preferenceEmbedHops" value="1" /> -->
<!-- <property name="canonicalizationPolicy">
<ref bean="canonicalizationPolicy" />
</property> -->
<!-- <property name="queueAssignmentPolicy">
<ref bean="queueAssignmentPolicy" />
</property> -->
<!-- <property name="uriPrecedencePolicy">
<ref bean="uriPrecedencePolicy" />
</property> -->
<!-- <property name="costAssignmentPolicy">
<ref bean="costAssignmentPolicy" />
</property> -->
</bean>
<!-- assembled into ordered CandidateChain bean -->
<bean id="candidateProcessors" class="org.archive.modules.CandidateChain">
<property name="processors">
<list>
<!-- apply scoping rules to each individual candidate URI... -->
<ref bean="candidateScoper"/>
<!-- ...then prepare those ACCEPTed for enqueuing to frontier. -->
<ref bean="preparer"/>
</list>
</property>
</bean>
<!-- FETCH CHAIN -->
<!-- processors declared as named beans -->
<bean id="preselector" class="org.archive.crawler.prefetch.Preselector">
<!-- <property name="recheckScope" value="false" /> -->
<!-- <property name="blockAll" value="false" /> -->
<!-- <property name="blockByRegex" value="" /> -->
<!-- <property name="allowByRegex" value="" /> -->
</bean>
<bean id="preconditions" class="org.archive.crawler.prefetch.PreconditionEnforcer">
<!-- <property name="ipValidityDurationSeconds" value="21600" /> -->
<!-- <property name="robotsValidityDurationSeconds" value="86400" /> -->
<!-- <property name="calculateRobotsOnly" value="false" /> -->
</bean>
<bean id="fetchDns" class="org.archive.modules.fetcher.FetchDNS">
<!-- <property name="acceptNonDnsResolves" value="false" /> -->
<!-- <property name="digestContent" value="true" /> -->
<!-- <property name="digestAlgorithm" value="sha1" /> -->
</bean>
<bean id="fetchHttp" class="org.archive.modules.fetcher.FetchHTTP">
<!-- <property name="maxLengthBytes" value="0" /> -->
<!-- <property name="timeoutSeconds" value="1200" /> -->
<!-- <property name="maxFetchKBSec" value="0" /> -->
<!-- <property name="defaultEncoding" value="ISO-8859-1" /> -->
<!-- <property name="shouldFetchBodyRule">
<bean class="org.archive.modules.deciderules.AcceptDecideRule"/>
</property> -->
<!-- <property name="soTimeoutMs" value="20000" /> -->
<!-- <property name="sendIfModifiedSince" value="true" /> -->
<!-- <property name="sendIfNoneMatch" value="true" /> -->
<!-- <property name="sendConnectionClose" value="true" /> -->
<!-- <property name="sendReferer" value="true" /> -->
<!-- <property name="sendRange" value="false" /> -->
<!-- <property name="ignoreCookies" value="false" /> -->
<!-- <property name="sslTrustLevel" value="OPEN" /> -->
<!-- <property name="acceptHeaders">
<list>
</list>
</property>
-->
<!-- <property name="httpBindAddress" value="" /> -->
<!-- <property name="httpProxyHost" value="" /> -->
<!-- <property name="httpProxyPort" value="0" /> -->
<!-- <property name="digestContent" value="true" /> -->
<!-- <property name="digestAlgorithm" value="sha1" /> -->
</bean>
<bean id="extractorHttp" class="org.archive.modules.extractor.ExtractorHTTP">
</bean>
<bean id="extractorHtml" class="org.archive.modules.extractor.ExtractorHTML">
<!-- <property name="extractJavascript" value="true" /> -->
<!-- <property name="extractValueAttributes" value="true" /> -->
<!-- <property name="ignoreFormActionUrls" value="false" /> -->
<!-- <property name="extractOnlyFormGets" value="true" /> -->
<!-- <property name="treatFramesAsEmbedLinks" value="true" /> -->
<!-- <property name="ignoreUnexpectedHtml" value="true" /> -->
<!-- <property name="maxElementLength" value="1024" /> -->
<!-- <property name="maxAttributeNameLength" value="1024" /> -->
<!-- <property name="maxAttributeValueLength" value="16384" /> -->
</bean>
<bean id="extractorCss" class="org.archive.modules.extractor.ExtractorCSS">
</bean>
<bean id="extractorJs" class="org.archive.modules.extractor.ExtractorJS">
</bean>
<bean id="extractorSwf" class="org.archive.modules.extractor.ExtractorSWF">
</bean>
<!-- assembled into ordered FetchChain bean -->
<bean id="fetchProcessors" class="org.archive.modules.FetchChain">
<property name="processors">
<list>
<!-- recheck scope, if so enabled... -->
<ref bean="preselector"/>
<!-- ...then verify or trigger prerequisite URIs fetched, allow crawling... -->
<ref bean="preconditions"/>
<!-- ...fetch if DNS URI... -->
<ref bean="fetchDns"/>
<!-- ...fetch if HTTP URI... -->
<ref bean="fetchHttp"/>
<!-- ...extract oulinks from HTTP headers... -->
<ref bean="extractorHttp"/>
<!-- ...extract oulinks from HTML content... -->
<ref bean="extractorHtml"/>
<!-- ...extract oulinks from CSS content... -->
<ref bean="extractorCss"/>
<!-- ...extract oulinks from Javascript content... -->
<ref bean="extractorJs"/>
<!-- ...extract oulinks from Flash content... -->
<ref bean="extractorSwf"/>
</list>
</property>
</bean>
<!-- DISPOSITION CHAIN -->
<!-- processors declared as named beans -->
<bean id="arcWriter" class="org.archive.modules.writer.ARCWriterProcessor">
<!-- <property name="compress" value="true" /> -->
<!-- <property name="prefix" value="IAH" /> -->
<!-- <property name="suffix" value="${HOSTNAME}" /> -->
<!-- <property name="maxFileSizeBytes" value="100000000" /> -->
<!-- <property name="poolMaxActive" value="1" /> -->
<!-- <property name="poolMaxWaitMs" value="300000" /> -->
<!-- <property name="skipIdenticalDigests" value="false" /> -->
<!-- <property name="maxTotalBytesToWrite" value="0" /> -->
<!-- <property name="directory" value="." /> -->
<!-- <property name="storePaths">
<list>
<value>arcs</value>
</list>
</property> -->
</bean>
<bean id="candidates" class="org.archive.crawler.postprocessor.CandidatesProcessor">
<!-- <property name="seedsRedirectNewSeeds" value="true" /> -->
</bean>
<bean id="disposition" class="org.archive.crawler.postprocessor.DispositionProcessor">
<!-- <property name="delayFactor" value="5.0" /> -->
<!-- <property name="minDelayMs" value="3000" /> -->
<!-- <property name="respectCrawlDelayUpToSeconds" value="300" /> -->
<!-- <property name="maxDelayMs" value="30000" /> -->
<!-- <property name="maxPerHostBandwidthUsageKbSec" value="0" /> -->
</bean>
<!-- assembled into ordered DispositionChain bean -->
<bean id="dispositionProcessors" class="org.archive.modules.DispositionChain">
<property name="processors">
<list>
<!-- write to aggregate archival files... -->
<ref bean="arcWriter"/>
<!-- ...send each outlink candidate URI to CandidatesChain,
and enqueue those ACCEPTed to the frontier... -->
<ref bean="candidates"/>
<!-- ...then update stats, shared-structures, frontier decisions -->
<ref bean="disposition"/>
</list>
</property>
</bean>
<!-- CRAWLCONTROLLER: Control interface, unifying context -->
<bean id="crawlController"
class="org.archive.crawler.framework.CrawlController">
<!-- <property name="maxToeThreads" value="25" /> -->
<!-- <property name="pauseAtStart" value="true" /> -->
<!-- <property name="pauseAtFinish" value="false" /> -->
<!-- <property name="recorderInBufferBytes" value="524288" /> -->
<!-- <property name="recorderOutBufferBytes" value="16384" /> -->
<!-- <property name="checkpointerPeriod" value="-1" /> -->
<!-- <property name="scratchDir" value="scratch" /> -->
<!-- <property name="checkpointsDir" value="checkpoints" /> -->
</bean>
<!-- FRONTIER: Record of all URIs discovered and queued-for-collection -->
<bean id="frontier"
class="org.archive.crawler.frontier.BdbFrontier">
<!-- <property name="holdQueues" value="true" /> -->
<!-- <property name="queueTotalBudget" value="-1" /> -->
<!-- <property name="balanceReplenishAmount" value="3000" /> -->
<!-- <property name="errorPenaltyAmount" value="100" /> -->
<!-- <property name="precedenceFloor" value="255" /> -->
<!-- <property name="queuePrecedencePolicy">
<bean class="org.archive.crawler.frontier.precedence.BaseQueuePrecedencePolicy" />
</property> -->
<!-- <property name="snoozeLongMs" value="300000" /> -->
<!-- <property name="retryDelaySeconds" value="900" /> -->
<!-- <property name="maxRetries" value="30" /> -->
<!-- <property name="recoveryDir" value="logs" /> -->
<!-- <property name="recoveryLogEnabled" value="true" /> -->
<!-- <property name="maxOutlinks" value="6000" /> -->
<!-- <property name="outboundQueueCapacity" value="50" /> -->
<!-- <property name="inboundQueueMultiple" value="3" /> -->
<!-- <property name="dumpPendingAtClose" value="false" /> -->
</bean>
<!-- URI UNIQ FILTER: Used by frontier to remember already-included URIs -->
<bean id="uriUniqFilter"
class="org.archive.crawler.util.BdbUriUniqFilter">
</bean>
<!--
OPTIONAL BUT RECOMMENDED BEANS
-->
<!-- ACTIONDIRECTORY: disk directory for mid-crawl operations
Running job will watch directory for new files with URIs,
scripts, and other data to be processed during a crawl. -->
<bean id="actionDirectory" class="org.archive.crawler.framework.ActionDirectory">
<!-- <property name="actionDir" value="action" /> -->
<!-- <property name="initialDelaySeconds" value="10" /> -->
<!-- <property name="delaySeconds" value="30" /> -->
</bean>
<!-- CRAWLLIMITENFORCER: stops crawl when it reaches configured limits -->
<bean id="crawlLimiter" class="org.archive.crawler.framework.CrawlLimitEnforcer">
<!-- <property name="maxBytesDownload" value="0" /> -->
<!-- <property name="maxDocumentsDownload" value="0" /> -->
<!-- <property name="maxTimeSeconds" value="0" /> -->
</bean>
<!--
OPTIONAL BEANS
Uncomment and expand as needed, or if non-default alternate
implementations are preferred.
-->
<!-- CANONICALIZATION POLICY -->
<!--
<bean id="canonicalizationPolicy"
class="org.archive.modules.canonicalize.RulesCanonicalizationPolicy">
<list>
<bean class="org.archive.modules.canonicalize.LowercaseRule" />
<bean class="org.archive.modules.canonicalize.StripUserinfoRule" />
<bean class="org.archive.modules.canonicalize.StripWWWNRule" />
<bean class="org.archive.modules.canonicalize.StripSessionIDs" />
<bean class="org.archive.modules.canonicalize.StripSessionCFIDs" />
<bean class="org.archive.modules.canonicalize.FixupQueryString" />
</list>
</bean>
-->
<!-- QUEUE ASSIGNMENT POLICY -->
<!--
<bean id="queueAssignmentPolicy"
class="org.archive.crawler.frontier.SurtAuthorityQueueAssignmentPolicy">
<property name="forceQueueAssignment" value="" />
<property name="deferToPrevious" value="true" />
<property name="parallelQueues" value="1" />
</bean>
-->
<!-- URI PRECEDENCE POLICY -->
<!--
<bean id="uriPrecedencePolicy"
class="org.archive.crawler.frontier.precedence.CostUriPrecedencePolicy">
</bean>
-->
<!-- COST ASSIGNMENT POLICY -->
<!--
<bean id="costAssignmentPolicy"
class="org.archive.crawler.frontier.UnitCostAssignmentPolicy">
</bean>
-->
<!-- CREDENTIAL STORE: HTTP authentication or FORM POST credentials -->
<!--
<bean id="credentialStore"
class="org.archive.modules.credential.CredentialStore">
</bean>
-->
<!--
REQUIRED STANDARD BEANS
It will be very rare to replace or reconfigure the following beans.
-->
<!-- STATISTICSTRACKER: standard stats/reporting collector -->
<bean id="statisticsTracker"
class="org.archive.crawler.reporting.StatisticsTracker" autowire="byName">
<!-- <property name="reportsDir" value="reports" /> -->
<!-- <property name="liveHostReportSize" value="20" /> -->
<!-- <property name="intervalSeconds" value="20" /> -->
<!-- <property name="keepSnapshotsCount" value="5" /> -->
<!-- <property name="liveHostReportSize" value="20" /> -->
</bean>
<!-- CRAWLERLOGGERMODULE: shared logging facility -->
<bean id="loggerModule"
class="org.archive.crawler.reporting.CrawlerLoggerModule">
<!-- <property name="path" value="logs" /> -->
<!-- <property name="crawlLogPath" value="crawl.log" /> -->
<!-- <property name="alertsLogPath" value="alerts.log" /> -->
<!-- <property name="progressLogPath" value="progress-statistics.log" /> -->
<!-- <property name="uriErrorsLogPath" value="uri-errors.log" /> -->
<!-- <property name="runtimeErrorsLogPath" value="runtime-errors.log" /> -->
<!-- <property name="nonfatalErrorsLogPath" value="nonfatal-errors.log" /> -->
</bean>
<!-- SHEETOVERLAYMANAGER: manager of sheets of contextual overlays
Autowired to include any SheetForSurtPrefix or
SheetForDecideRuled beans -->
<bean id="sheetOverlaysManager" autowire="byType"
class="org.archive.crawler.spring.SheetOverlaysManager">
</bean>
<!-- BDBMODULE: shared BDB-JE disk persistence manager -->
<bean id="bdb"
class="org.archive.bdb.BdbModule">
<!-- <property name="dir" value="state" /> -->
<!-- <property name="cachePercentage" value="60" /> -->
<!-- <property name="useSharedCache" value="true" /> -->
<!-- <property name="checkpointCopyLogs" value="true" /> -->
<!-- <property name="expectedConcurrency" value="25" /> -->
</bean>
<!-- BDBCOOKIESTORAGE: disk-based cookie storage for FetchHTTP -->
<bean id="cookieStorage"
class="org.archive.modules.fetcher.BdbCookieStorage">
<!-- <property name="cookiesLoadFile"><null/></property> -->
<!-- <property name="cookiesSaveFile"><null/></property> -->
<!-- <property name="bdb">
<ref bean="bdb"/>
</property> -->
</bean>
<!-- SERVERCACHE: shared cache of server/host info -->
<bean id="serverCache"
class="org.archive.modules.net.BdbServerCache">
<!-- <property name="bdb">
<ref bean="bdb"/>
</property> -->
</bean>
<!-- CONFIG PATH CONFIGURER: required helper making crawl paths relative
to crawler-beans.cxml file, and tracking crawl files for web UI -->
<bean id="configPathConfigurer"
class="org.archive.spring.ConfigPathConfigurer">
</bean>
</beans>