SHELL=bash -o pipefail PATH:=$(CURDIR)/bin:$(PATH) export PATH all: dat/index.txt fix: grep -rl '

503' dat | xargs rm -fv -- dat: mkdir -p $@ dat/cdxindex.txt: | dat cdxget 'url=www.unicode.org/Public/*' 'fl=urlkey' 'filter=statuscode:200' 'filter=urlkey:.*(cvt|convert)utf.*' > $@ dat/urlkeys.txt: dat/cdxindex.txt cat $^ | cut -d '?' -f1 | sort -u > $@ dat/urlkeys.mk: dat/urlkeys.txt cat $^ | sed 's/^/urlkeys+=/' < $< > $@ -include dat/urlkeys.mk dat/each-cdx/%.txt: @mkdir -p '$(@D)' cdxget "url=$$(urlkey2url '$*')" 'filter=statuscode:200' 'collapse=digest' 'fl=timestamp,original' > '$@' dat/index.txt: $(addprefix dat/each-cdx/,$(addsuffix .txt,$(urlkeys))) cat -- $(foreach c,$^,'$c') | sort > $@ .DELETE_ON_ERROR: .SECONDARY: