# # ChangeLog for main/trunk/model-sites-dev/commoncrawl/siteConfig.xml # # Generated by Trac 1.4.2 # 2024-06-06T23:08:02+12:00 Sat, 30 May 2020 04:01:47 GMT ak19 [34132] * main/trunk/model-sites-dev/commoncrawl (added) * main/trunk/model-sites-dev/commoncrawl/collect (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/etc (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/etc/all_isMRIPages_forManual_containsMRIDomainListing.txt (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/etc/collectionConfig.bak (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/etc/collectionConfig.xml (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/etc/oai-inf.jdb (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/etc/oai-inf.jdb.bak (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/etc/oai-inf.lg (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/images (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/metadata (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/metadata/ex.mds (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/metadata/greenstone.mds (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/metadata/profile.xml (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/script (added) * main/trunk/model-sites-dev/commoncrawl/collect/allIsMRIForDomainShortlist/style (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/etc (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/etc/collectionConfig.bak (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/etc/collectionConfig.xml (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/etc/isMRI_urls.txt (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/etc/oai-inf.jdb (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/etc/oai-inf.jdb.bak (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/etc/oai-inf.lg (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/images (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/metadata (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/metadata/ex.mds (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/metadata/greenstone.mds (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/metadata/profile.xml (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/script (added) * main/trunk/model-sites-dev/commoncrawl/collect/allismri/style (added) * main/trunk/model-sites-dev/commoncrawl/etc (added) * main/trunk/model-sites-dev/commoncrawl/import_nutchDumpTxtsOfcrawledMRICC.tar.gz (added) * main/trunk/model-sites-dev/commoncrawl/moveDumpTxtFilesIntoImport.sh (added) * main/trunk/model-sites-dev/commoncrawl/resources (added) * main/trunk/model-sites-dev/commoncrawl/resources/siteConfig.properties (added) * main/trunk/model-sites-dev/commoncrawl/siteConfig.xml (added) Committing the commoncrawl site of Nutch recrawls of our CC data ...