PATH:=$(CURDIR)/bin:$(PATH) export PATH all: each-cdx dat: mkdir -p $@ dat/ftp.txt: | dat cdxget 'url=ftp.unicode.org/Public/*' 'fl=urlkey' 'filter=statuscode:200' 'filter=urlkey:.*(cvt|convert)utf.*' > $@ dat/www.txt: | dat cdxget 'url=www.unicode.org/Public/*' 'fl=urlkey' 'filter=statuscode:200' 'filter=urlkey:.*(cvt|convert)utf.*' > $@ dat/urlkeys.txt: dat/ftp.txt dat/www.txt cat $^ | cut -d '?' -f1 | sed 's/,ftp)/)/' | sort -u > $@ dat/urlkeys.mk: dat/urlkeys.txt cat $^ | sed 's/^/urlkeys+=/' < $< > $@ -include dat/urlkeys.mk rp = ) c = , all_urlkeys = $(urlkeys) $(subst $(rp),$(c)ftp$(rp),$(urlkeys)) dat/each-cdx/%.txt: mkdir -p '$(@D)' cdxget "url=$$(urlkey2url '$*')" 'filter=statuscode:200' 'collapse=digest' 'fl=timestamp,original' > '$@' each-cdx: $(addprefix dat/each-cdx/,$(addsuffix .txt,$(all_urlkeys))) .PHONY: each-cdx .DELETE_ON_ERROR: .SECONDARY: