################################################################################
##
## Copyright (c) 2007-2011 Illumina, Inc.
##
## This software is covered by the "Illumina Genome Analyzer Software
## License Agreement" and the "Illumina Source Code License Agreement",
## and certain third party copyright/licenses, and any user of this
## source file is bound by the terms therein (see accompanying files
## Illumina_Genome_Analyzer_Software_License_Agreement.pdf and
## Illumina_Source_Code_License_Agreement.pdf and third party
## copyright/license notices).
##
## This file is part of the Consensus Assessment of Sequence And VAriation
## (CASAVA) software package.
##
## file SingleAux.mk
##
## brief Partial makefile to pick the best alignments.
##
## author Roman Petrovski
##
################################################################################
ifeq (,$(currentSetList))
$(error $(dataset): empty list of sets)
endif

currentSetName := $(word 1, $(currentSetList))
currentSet := $($(dataset)_ELAND_SET_$(currentSetName))

ifeq (1,$(words $(currentSetList)))
currentSetList :=
else
currentSetList := $(wordlist 2, $(words $(currentSetList)), $(currentSetList))
endif

kagu_target:=$($(dataset)_DESTINATION_PREFIX)_R$(read)_$(currentSetName)$(EXPORT_SUFFIX)

kagu_eland_extended_prereqs:=$($(dataset)_TEMP_PREFIX)_R$(read)_$(currentSetName)$(ELAND_RESULT_EXTENDED)

$(dataset)_kagu_params:= $($(dataset)_KAGU_PARAMS)
ifeq (contigName,$($(dataset)_CHROM_NAME_SOURCE))
  $(dataset)_kagu_params += --ucn
endif

.PRECIOUS: $(kagu_target)
$(kagu_target): ELAND_RESULT_EXTENDED := $(ELAND_RESULT_EXTENDED)
$(kagu_target): EXPORT_SUFFIX := $(EXPORT_SUFFIX)
$(kagu_target): GENOMESIZE_SUFFIX := $(GENOMESIZE_SUFFIX)
$(kagu_target): read := $(read)
$(kagu_target): currentSetName :=  $(currentSetName)
$(kagu_target): currentSet :=  $(currentSet)
$(kagu_target): \
  $($(dataset)_TEMP_PREFIX)_R$(read)_$(currentSetName)$(ELAND_RESULT_EXTENDED) \
  $($(dataset)_TEMP_PREFIX)_R$(read)_$(currentSetName)$(ELAND_RESULT_CONTAM) \
  $($(dataset)_TEMP_PREFIX)_R$(read)_$(currentSetName)$(ELAND_RESULT_SPLICE) \
  $($(dataset)_DESTINATION_PREFIX)$(GENOMESIZE_SUFFIX)
	$(CMDPREFIX) $(PICK_BEST_ALIGNMENT) \
	  --ie1 "$($(dataset)_TEMP_PREFIX)_R$(read)_$(currentSetName)$(ELAND_RESULT_EXTENDED)" \
	  --ic "$($(dataset)_TEMP_PREFIX)_R$(read)_$(currentSetName)$(ELAND_RESULT_CONTAM)" \
	  --is "$($(dataset)_TEMP_PREFIX)_R$(read)_$(currentSetName)$(ELAND_RESULT_SPLICE)" \
	  $(foreach fastq_set, $(currentSet), \
	      --if1 "$(EXPT_DIR)/$($(dataset)_SOURCE_PREFIX)_R$(read)_$(fastq_set).fastq.gz") \
	  --irs "$($(dataset)_DESTINATION_PREFIX)$(GENOMESIZE_SUFFIX)" \
	  --sl1 "$($(dataset)_ELAND_SEED_LENGTH$(read))" \
	  --ub1 "$($(dataset)_USE_BASES$(read))" \
	  --oe1 $($(dataset)_DESTINATION_PREFIX)_R$(read)_$(currentSetName)$(EXPORT_SUFFIX).tmp \
	   $($(dataset)_kagu_params) 1>&2 \
	$(AND) $(MV) $($(dataset)_DESTINATION_PREFIX)_R$(read)_$(currentSetName)$(EXPORT_SUFFIX).tmp.gz $($(dataset)_DESTINATION_PREFIX)_R$(read)_$(currentSetName)$(EXPORT_SUFFIX)

rnaqc_target:=$($(dataset)_STATS_DIR)/$($(dataset)_FILE_PREFIX)_R$(read)_$(currentSetName)$(RNAQC_SUFFIX)

# RNAQC rule prints contaminants alignment and other statistics for each lane
.PRECIOUS: $(rnaqc_target)
$(rnaqc_target): EXPORT_SUFFIX := $(EXPORT_SUFFIX)
$(rnaqc_target): dataset := $(dataset)
$(rnaqc_target): read := $(read)
$(rnaqc_target): currentSetName :=  $(currentSetName)
$(rnaqc_target): \
  $($(dataset)_DESTINATION_PREFIX)_R$(read)_$(currentSetName)$(CONTAM_EXPORT_SUFFIX) \
  $($(dataset)_DESTINATION_PREFIX)_R$(read)_$(currentSetName)$(EXPORT_SUFFIX) \
  $(dir $(rnaqc_target)).sentinel
	$(CMDPREFIX) \
    ( ( ( $(GUNZIP) -c $($(dataset)_DESTINATION_PREFIX)_R$(read)_$(currentSetName)$(EXPORT_SUFFIX) \
      |$(TEE) >( $(ECHO) -e "$($(dataset)_RNAQC_COUNT_CLUSTERS_NAME)\t"`$($(dataset)_RNAQC_COUNT_CLUSTERS_CMD)` >&3) \
      |( $(EGREP) 'Y$$' $(OR) $(EXIT) 0 ) \
      |$(TEE) >( $(ECHO) -e "$($(dataset)_RNAQC_COUNT_PF_NAME)\t"`$($(dataset)_RNAQC_COUNT_PF_CMD)` >&3) \
      |$(TEE) >( $(ECHO) -e "$($(dataset)_RNAQC_COUNT_USABLE_NAME)\t"`$($(dataset)_RNAQC_COUNT_USABLE_CMD)` >&3) \
      |$(CUT) -f11 \
      |$(TEE) >( $(ECHO) -e "$($(dataset)_RNAQC_COUNT_QC_NAME)\t"`$($(dataset)_RNAQC_COUNT_QC_CMD)` >&3) \
      |$(TEE) >( $(ECHO) -e "$($(dataset)_RNAQC_COUNT_NM_NAME)\t"`$($(dataset)_RNAQC_COUNT_NM_CMD)` >&3) \
      |$(TEE) >( $(ECHO) -e "$($(dataset)_RNAQC_COUNT_RM_NAME)\t"`$($(dataset)_RNAQC_COUNT_RM_CMD)` >&3) \
      |$(TEE) >( $(ECHO) -e "$($(dataset)_RNAQC_COUNT_SPLICE_NAME)\t"`$($(dataset)_RNAQC_COUNT_SPLICE_CMD)` >&3) \
      |$(TEE) >( $(ECHO) -e "$($(dataset)_RNAQC_COUNT_GENOME_NAME)\t"`$($(dataset)_RNAQC_COUNT_GENOME_CMD)` >&3) \
      >/dev/null) 3>&1) \
     $(AND) \
     ( $(GUNZIP) -c $($(dataset)_DESTINATION_PREFIX)_R$(read)_$(currentSetName)$(CONTAM_EXPORT_SUFFIX) \
      |( $(EGREP) 'Y$$' $(OR) $(EXIT) 0) \
      |$(CUT) -f11 \
      |$($(dataset)_RNAQC_FIND_CONTAMS_CMD) \
      |$(SORT) \
      |$(UNIQ) -c \
      |$(AWK) '{print $$2"\t"$$1}' \
     ) \
    ) \
    > $(SAFEPIPETARGET)