Parallelize wc by implementing map/reduce in make

wc.mk

#!/usr/bin/make -Rrf
# Parallelize wc by implementing map/reduce in make
# Written by Shaun Jackman.

# Number of chunks
n=4

all: words.wc words.mapreduce.wc

clean:
	rm -f words.wc words.mapreduce.wc words.[0-9][0-9]

test: words.wc words.mapreduce.wc
	diff -sw $^

.PHONY: all clean test
.DELETE_ON_ERROR:

# Input data
words: /usr/share/dict/words
	ln -s $< $@

# Partition
chunks=$(foreach i,$(shell seq -f%02.0f 0 $$(($n-1))),%.$i)
$(chunks): %
	split -dnl/$n $< $*.

# Map
%.wc: %
	wc $< >$@

# Reduce
%.mapreduce.wc: $(foreach i,$(chunks),$i.wc)
	awk '{a+=$$1; b+=$$2; c+=$$3} END {print a, b, c, "$*"}' $^ >$@

Very neat!

Perhaps you should use "mktemp" to get a directory for the temp files.

Often /tmp points to a much faster disk (SSD) which could speed things up, but I guess it could also not be large enough.