plesna/Makefile

DATA_BASE=./datas

PDF_BASE=$(DATA_BASE)/pdfs
PDF_YEARS=$(wildcard $(PDF_BASE)/*)

RAW_BASE=$(DATA_BASE)/raw
RAW_CRG=$(RAW_BASE)/CRG
RAW_CRG_YEARS=$(subst $(PDF_BASE), $(RAW_CRG), $(PDF_YEARS))


$(RAW_CRG)/%/: $(wildcard $(PDF_BASE)/%/*)
	echo $(wildcard $(PDF_BASE)/$*/*)
	@echo ----
	ls $(PDF_BASE)/$*/
	@echo ----
	echo $*
	@echo ----
	echo $^
	@echo ----
	echo $?

#./datas/raw/CRG/%: 
#pdf-oralia extract all --src $$year --dest $$(subst $$PDF_BASE, $$RAW_CRG, $$year)
# $(RAW_CRG_YEARS): $(PDF_PATHS)
# 	for year in $(PDF_PATHS); do \
# 		echo $$year; \
# 		echo $$(subst $$PDF_BASE, $$RAW_CRG, $$year); \
# 		echo "----"; \
# 	done;

extract_pdfs:
	for year in 2021 2022 2023 2024; do \
		mkdir -p $(RAW_CRG)/$$year/extracted;\
		pdf-oralia extract all --src $(PDF_BASE)/$$year/ --dest $(RAW_CRG)/$$year/extracted; \
		pdf-oralia join --src $(RAW_CRG)/$$year/extracted/ --dest $(RAW_CRG)/$$year/; \
	done

clean_raw:
	rm -rf ./PLESNA Compta SYSTEM/raw/**/*.csv

clean_built:
	rm -rf $(DATA_BASE)/staging/**/*.csv
	rm -rf $(DATA_BASE)/gold/**/*.csv
	rm -rf $(DATA_BASE)/datamart/**/*.csv
	rm -rf $(DATA_BASE)/datamart/**/*.xlsx

run_ingest:
	python -m scripts ingest

run_feature:
	python -m scripts feature

run_datamart:
	python -m scripts datamart

build: clean_built run_ingest run_feature run_datamart

clean_all: clean_built clean_raw

import_nextcloud:
	rsync -av ~/Nextcloud/PLESNA\ Compta\ SYSTEM/Histoire/ ./datas/Histoire

push_nextcloud:
	rsync -av ./datas/datamart/ ~/Nextcloud/PLESNA\ Compta\ SYSTEM/DataMart