Skip to content

build method should return interface instead of implementation & add google.com to GooglebotData #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tfeiner wants to merge 2 commits into
base: master
Choose a base branch
from
Open

build method should return interface instead of implementation & add google.com to GooglebotData #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9ec2ad9
build method should return interface instead of implementation + form…
May 15, 2017
8280a4c
add "google.com" to HOSTNAMES according to https://support.google.com…
May 18, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/main/java/com/optimaize/webcrawlerverifier/bots/GooglebotData.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ public boolean apply(String userAgent) {
}
};

private static final ImmutableSet<String> HOSTNAMES = ImmutableSet.of("googlebot.com");
private static final ImmutableSet<String> HOSTNAMES = ImmutableSet.of("googlebot.com", "google.com");


private static final GooglebotData INSTANCE = new GooglebotData();
Expand Down
16 changes: 9 additions & 7 deletions src/main/java/com/optimaize/webcrawlerverifier/bots/KnownHostBotVerifierBuilder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,18 +19,19 @@ public class KnownHostBotVerifierBuilder {


public KnownHostBotVerifierBuilder crawlerData(@NotNull CrawlerData crawlerData) {
if (this.crawlerData!=null) throw new IllegalStateException("The crawlerData was set already!");
if (this.crawlerData != null) throw new IllegalStateException("The crawlerData was set already!");
this.crawlerData = crawlerData;
return this;
}

/**
*/
public KnownHostBotVerifierBuilder dnsVerifier(@NotNull ReverseDnsVerifier dnsVerifier) {
if (this.dnsVerifier!=null) throw new IllegalStateException("The dnsVerifier was set already!");
if (this.dnsVerifier != null) throw new IllegalStateException("The dnsVerifier was set already!");
this.dnsVerifier = dnsVerifier;
return this;
}

/**
* Uses the {@link DnsjavaReverseDnsVerifier} with the default name server(s) provided by the system.
*/
Expand All @@ -43,26 +44,27 @@ public KnownHostBotVerifierBuilder dnsVerifierDefault() {
* If you must, for testing, then pass in a dummy cache that drops all.
*/
public KnownHostBotVerifierBuilder dnsResultCache(@NotNull Cache<String, BotCheckerResult> dnsResultCache) {
if (this.dnsResultCache !=null) throw new IllegalStateException("The dnsResultCache was set already!");
if (this.dnsResultCache != null) throw new IllegalStateException("The dnsResultCache was set already!");
this.dnsResultCache = dnsResultCache;
return this;
}

/**
* Uses maximumSize(1_000) and expireAfterWrite(3*24, TimeUnit.HOURS)
*/
public KnownHostBotVerifierBuilder dnsResultCacheDefault() {
Cache<String, BotCheckerResult> cache = CacheBuilder.newBuilder()
.maximumSize(1_000)
.expireAfterWrite(3*24, TimeUnit.HOURS)
.expireAfterWrite(3 * 24, TimeUnit.HOURS)
.build();
return dnsResultCache(cache);
}


@NotNull
public KnownHostBotVerifierImpl build() {
if (dnsVerifier==null) throw new IllegalArgumentException("No dnsVerifier provided!");
if (dnsResultCache ==null) throw new IllegalArgumentException("No cache provided!");
public KnownHostBotVerifier build() {
if (dnsVerifier == null) throw new IllegalArgumentException("No dnsVerifier provided!");
if (dnsResultCache == null) throw new IllegalArgumentException("No cache provided!");
return new KnownHostBotVerifierImpl(crawlerData, dnsVerifier, dnsResultCache);
}

Expand Down