GitLabのmainブランチをクロール対象にしたくてcommit_idにブランチ名を指定して試してみたのですがエラーが発生しました。
設定に何か不備があったりしますでしょうか?
パラメーター
uri=https://gitlab.com/graphviz/graphviz.git
base_url=https://gitlab.com/graphviz/graphviz/-/tree/main
commit_id=main
extractors=text/.*:textExtractor,application/xml:textExtractor,application/javascript:textExtractor
delete_old_docs=false
スクリプト
url=url
host="gitlab.com"
site="gitlab.com/graphviz/graphviz/" + path
title=name
content=content
cache=""
digest=author.toExternalString()
anchor=
content_length=contentLength
last_modified=timestamp
mimetype=mimetype
クロールログ
2022-06-29 21:10:02,256 [main] INFO Starting Crawler..
2022-06-29 21:10:02,549 [Ewher4EBom8xRIppAq5u-1] INFO Git: https://gitlab.com/graphviz/graphviz.git
2022-06-29 21:10:34,662 [Ewher4EBom8xRIppAq5u-1] INFO Created fess_crawler.data index.
2022-06-29 21:10:34,893 [Ewher4EBom8xRIppAq5u-1] INFO Created fess_crawler.data mapping.
2022-06-29 21:10:38,358 [Ewher4EBom8xRIppAq5u-1] INFO Created fess_crawler.queue index.
2022-06-29 21:10:38,576 [Ewher4EBom8xRIppAq5u-1] INFO Created fess_crawler.queue mapping.
2022-06-29 21:10:42,126 [Ewher4EBom8xRIppAq5u-1] INFO Created fess_crawler.filter index.
2022-06-29 21:10:42,285 [Ewher4EBom8xRIppAq5u-1] INFO Created fess_crawler.filter mapping.
2022-06-29 21:10:42,342 [Ewher4EBom8xRIppAq5u-1] WARN Crawling Access Exception at : {expires=Sat Jul 02 21:10:02 JST 2022, role=[Rguest], config_id=DEwher4EBom8xRIppAq5u, created=Wed Jun 29 21:10:02 JST 2022, segment=Ewher4EBom8xRIppAq5u, boost=1.0, mimetype=application/datastore, virtual_host=[]}
org.eclipse.jgit.api.errors.NoHeadException: No HEAD exists and no explicit starting revision was specified
at org.eclipse.jgit.api.LogCommand.call(LogCommand.java:131) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.getRevCommit(GitDataStore.java:400) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.processFile(GitDataStore.java:272) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.lambda$storeData$0(GitDataStore.java:189) ~[fess-ds-git-14.2.0.jar:?]
at java.util.ArrayList.forEach(ArrayList.java:1511) [?:?]
at org.codelibs.fess.ds.git.GitDataStore.storeData(GitDataStore.java:178) [fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.AbstractDataStore.store(AbstractDataStore.java:122) [classes/:?]
at org.codelibs.fess.helper.DataIndexHelper$DataCrawlingThread.process(DataIndexHelper.java:218) [classes/:?]
at org.codelibs.fess.helper.DataIndexHelper$DataCrawlingThread.run(DataIndexHelper.java:204) [classes/:?]
2022-06-29 21:10:42,519 [Ewher4EBom8xRIppAq5u-1] WARN Crawling Access Exception at : {expires=Sat Jul 02 21:10:02 JST 2022, role=[Rguest], config_id=DEwher4EBom8xRIppAq5u, created=Wed Jun 29 21:10:02 JST 2022, segment=Ewher4EBom8xRIppAq5u, boost=1.0, mimetype=application/datastore, virtual_host=[]}
org.eclipse.jgit.api.errors.NoHeadException: No HEAD exists and no explicit starting revision was specified
at org.eclipse.jgit.api.LogCommand.call(LogCommand.java:131) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.getRevCommit(GitDataStore.java:400) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.processFile(GitDataStore.java:272) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.lambda$storeData$0(GitDataStore.java:189) ~[fess-ds-git-14.2.0.jar:?]
at java.util.ArrayList.forEach(ArrayList.java:1511) [?:?]
at org.codelibs.fess.ds.git.GitDataStore.storeData(GitDataStore.java:178) [fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.AbstractDataStore.store(AbstractDataStore.java:122) [classes/:?]
at org.codelibs.fess.helper.DataIndexHelper$DataCrawlingThread.process(DataIndexHelper.java:218) [classes/:?]
at org.codelibs.fess.helper.DataIndexHelper$DataCrawlingThread.run(DataIndexHelper.java:204) [classes/:?]
2022-06-29 21:10:42,660 [Ewher4EBom8xRIppAq5u-1] WARN Crawling Access Exception at : {expires=Sat Jul 02 21:10:02 JST 2022, role=[Rguest], config_id=DEwher4EBom8xRIppAq5u, created=Wed Jun 29 21:10:02 JST 2022, segment=Ewher4EBom8xRIppAq5u, boost=1.0, mimetype=application/datastore, virtual_host=[]}
org.eclipse.jgit.api.errors.NoHeadException: No HEAD exists and no explicit starting revision was specified
at org.eclipse.jgit.api.LogCommand.call(LogCommand.java:131) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.getRevCommit(GitDataStore.java:400) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.processFile(GitDataStore.java:272) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.lambda$storeData$0(GitDataStore.java:189) ~[fess-ds-git-14.2.0.jar:?]
at java.util.ArrayList.forEach(ArrayList.java:1511) [?:?]
at org.codelibs.fess.ds.git.GitDataStore.storeData(GitDataStore.java:178) [fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.AbstractDataStore.store(AbstractDataStore.java:122) [classes/:?]
at org.codelibs.fess.helper.DataIndexHelper$DataCrawlingThread.process(DataIndexHelper.java:218) [classes/:?]
at org.codelibs.fess.helper.DataIndexHelper$DataCrawlingThread.run(DataIndexHelper.java:204) [classes/:?]
2022-06-29 21:10:42,773 [Ewher4EBom8xRIppAq5u-1] WARN Crawling Access Exception at : {expires=Sat Jul 02 21:10:02 JST 2022, role=[Rguest], config_id=DEwher4EBom8xRIppAq5u, created=Wed Jun 29 21:10:02 JST 2022, segment=Ewher4EBom8xRIppAq5u, boost=1.0, mimetype=application/datastore, virtual_host=[]}
org.eclipse.jgit.api.errors.NoHeadException: No HEAD exists and no explicit starting revision was specified
at org.eclipse.jgit.api.LogCommand.call(LogCommand.java:131) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.getRevCommit(GitDataStore.java:400) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.processFile(GitDataStore.java:272) ~[fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.git.GitDataStore.lambda$storeData$0(GitDataStore.java:189) ~[fess-ds-git-14.2.0.jar:?]
at java.util.ArrayList.forEach(ArrayList.java:1511) [?:?]
at org.codelibs.fess.ds.git.GitDataStore.storeData(GitDataStore.java:178) [fess-ds-git-14.2.0.jar:?]
at org.codelibs.fess.ds.AbstractDataStore.store(AbstractDataStore.java:122) [classes/:?]
at org.codelibs.fess.helper.DataIndexHelper$DataCrawlingThread.process(DataIndexHelper.java:218) [classes/:?]
at org.codelibs.fess.helper.DataIndexHelper$DataCrawlingThread.run(DataIndexHelper.java:204) [classes/:?]
2022-06-29 21:10:42,884 [Ewher4EBom8xRIppAq5u-1] WARN Crawling Access Exception at : {expires=Sat Jul 02 21:10:02 JST 2022, role=[Rguest], config_id=DEwher4EBom8xRIppAq5u, created=Wed Jun 29 21:10:02 JST 2022, segment=Ewher4EBom8xRIppAq5u, boost=1.0, mimetype=application/datastore, virtual_host=[]}
...