export CITEFILE=enwiki-YYYYMMDD-pages-articles.citations.json.gz

# total number of articles processed
zcat $CITEFILE | wc -l

# articles with one or more refs
zcat $CITEFILE | rg '"CitationClass"' | wc -l

# total number of refs
zcat $CITEFILE | jq '.refs[].CitationClass' -r | wc -l

# refs by type
zcat $CITEFILE | jq '.refs[].CitationClass' -r | sort | uniq -c | sort -nr

# identifiers present
zcat $CITEFILE | jq '.refs[] | select(.ID_list != null) | .ID_list | keys[]' -r | sort | uniq -c | sort -nr

# refs with URL, by type
zcat $CITEFILE | jq '.refs[] | select(.URL != null) | .CitationClass' -r | sort | uniq -c | sort -nr

# refs with URL, by type
zcat $CITEFILE | jq '.refs[] | select(.ArchiveURL != null) | .CitationClass' -r | sort | uniq -c | sort -nr