diff options
| author | Luke Shumaker <lukeshu@lukeshu.com> | 2017-07-01 19:10:47 -0400 |
|---|---|---|
| committer | Luke Shumaker <lukeshu@lukeshu.com> | 2017-07-01 19:10:47 -0400 |
| commit | bc0107813be28ab9532f136047d23bbaa158ee8b (patch) | |
| tree | a58775772295b25d4955124be85159926cf3c88a /Makefile | |
| parent | 55f9bd8d5226eb49f5899c5ddca89c655ef96e9b (diff) | |
fixo
Diffstat (limited to 'Makefile')
| -rw-r--r-- | Makefile | 33 |
1 files changed, 24 insertions, 9 deletions
@@ -6,41 +6,52 @@ url2murl = $(subst %,^25,$(subst :,^3A,$(subst ^,^5E,$1))) murl2url = $(subst ^5E,^,$(subst ^3A,:,$(subst ^25,%,$1))) dirfail = ( r=$$?; mv -- '$@'{,.bak}; exit $$r; ) -all: dat/git dat/pools +all: + $(MAKE) dat/urlkeys.mk + $(MAKE) dat/index.mk + $(MAKE) dat/pools fix: grep -rl '<html><body><h1>503' dat | xargs rm -fv -- +.PHONY: all fix + +# Stage 1 ###################################################################### + 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 > $@ + < $< cut -d '?' -f1 | sort -u > $@ dat/urlkeys.mk: dat/urlkeys.txt - cat $^ | sed 's/^/urlkeys+=/' < $< > $@ + < $< sed 's/^/urlkeys+=/' > $@ --include dat/urlkeys.mk +# Stage 2 ###################################################################### +ifneq ($(wildcard dat/urlkeys.mk),) +include dat/urlkeys.mk dat/each-cdx/%.txt: @mkdir -p '$(@D)' cdxget "url=$$(urlkey2url '$*')" 'filter=statuscode:200' 'collapse=digest' 'fl=timestamp,original' > '$@' -dat/index.txt: $(addprefix dat/each-cdx/,$(addsuffix .txt,$(urlkeys))) urlkeys.txt +dat/index.txt: $(addprefix dat/each-cdx/,$(addsuffix .txt,$(urlkeys))) dat/urlkeys.txt cat -- $(foreach c,$(filter dat/each-cdx/%,$^),'$c') | sort > $@ dat/index.mk: dat/index.txt < $< sed -e 's,^,index+=,' -e 's, ,/,' > $@ +# Stage 3 ###################################################################### +ifneq ($(wildcard dat/index.mk),) -include dat/index.mk dat/content-dir/%/index.wahtml: @mkdir -p '$(@D)' curl -s 'http://web.archive.org/web/$(call murl2url,$*)' > $@ dat/content-dir/%/index.html: dat/content-dir/%/index.wahtml - wayfore < $< > $@ + < $< wayfore > $@ dat/content-dir/%/readme.txt: dat/content-dir/%/index.html < $< sed -n '/^<pre>$$/,/<\/pre>/p' | sed -e 1d -e 's,</pre>.*,,' > $@ dat/content-dir/%/metadata.txt: dat/content-dir/%/index.html - < $< grep '^<img' | sed 's/<[^>]*>//g' | fmt-metadata $(firstword $(subst /, ,$*)) > $@ + < $< grep '^<img' | sed 's/<[^>]*>//g' | grep -vi 'parent directory' | fmt-metadata $(firstword $(subst /, ,$*)) > $@ content-dir = $(foreach u,$(filter %/,$(index)),dat/content-dir/$(call url2murl,$(u))) download += $(addsuffix readme.txt,$(content-dir)) $(addsuffix metadata.txt,$(content-dir)) @@ -51,9 +62,10 @@ content-file = $(foreach u,$(filter-out %/,$(index)),dat/content-file/$(call url download += $(content-file) download: $(download) +.PHONY: download dat/pools.txt: $(addsuffix metadata.txt,$(content-dir)) dat/index.txt - grep ^ $(foreach c,$(filter %/metadata.txt,$^),'$c') | bin/dateify | sed -r -e 's,.*web\.archive\.org/web/,,' -e 's,/.*/Public/, ,' -e 's,/metadata\.txt: ,/,' -e 's,\s+, ,g' | sort -u > $@ + grep ^ $(foreach c,$(filter %/metadata.txt,$^),'$c') | sed -r -e 's,^dat/content-dir/,,' -e 's,/.*/Public/, ,' -e 's,/metadata\.txt:,/,' -e 's,\s+, ,g' | sort -u > $@ dat/pools: $(download) dat/pools.txt dat/index.txt rm -rf -- $@ $@.bak poolify dat/pools.txt dat/index.txt || $(dirfail) @@ -62,6 +74,9 @@ dat/git: $(download) dat/index.txt rm -rf -- $@ $@.bak gitthing dat/git < dat/index.txt || $(dirfail) -.PHONY: all fix download +################################################################################ +endif +endif + .DELETE_ON_ERROR: .SECONDARY: |