translation/tools/mosesdecoder/contrib/m4m/modules/mmbitext.m4m

# -*- makefile -*-

# Makefile for building a Moses system from a word-aligned corpus
# (c) 2011 - 2012 Ulrich Germann

define mmap_ttrack

$2/$(notdir $1).mct: | $2/$(notdir $1).tdx
$2/$(notdir $1).tdx: | $2/$(notdir $1).sfa
$2/$(notdir $1).sfa: | $(strip $1).txt.gz
	$$(lock)
	zcat -f $(strip $1).txt.gz \
	| ${MOSES_BIN}/mtt-build -i -o $$@.lock/$$(basename $${@F})
	mv $$@.lock/$$(basename $${@F}).tdx $${@D}
	mv $$@.lock/$$(basename $${@F}).sfa $${@D}
	mv $$@.lock/$$(basename $${@F}).mct $${@D}
	$$(unlock)

endef

# $1: base name of word-aligned corpus in text format
# $2: directory for mmapped bitext
define mmap_bitext

$(call mmap_ttrack,$1${L1},$2)
$(call mmap_ttrack,$1${L2},$2)
$2/$(notdir $1)${L1}-${L2}.mam: SYMAL = $(strip $1)${L1}-${L2}.symal.gz
$2/$(notdir $1)${L1}-${L2}.mam: | $(strip $1)${L1}-${L2}.symal.gz
	$$(lock)
	zcat -f $${SYMAL} | ${MOSES_BIN}/symal2mam $$@_ && mv $$@_ $$@ 
	$$(unlock)

$2/$(notdir $1)${L1}-${L2}.lex: | $2/$(notdir $1)${L1}.mct
$2/$(notdir $1)${L1}-${L2}.lex: | $2/$(notdir $1)${L2}.mct
$2/$(notdir $1)${L1}-${L2}.lex: | $2/$(notdir $1)${L1}-${L2}.mam
	$$(lock)
	${MOSES_BIN}/mmlex-build $2/$(notdir $1) ${L1} ${L2} \
	-o $$@.lock/$${@F} -c $$@.lock/$$(basename $${@F}).coc 
	mv $$@.lock/$${@F} $${@D}
	mv $$@.lock/$$(basename $${@F}).coc $${@D}
	$$(unlock)

endef