new makefile

This commit is contained in:
rjawor 2019-06-26 08:47:01 +02:00
parent 9639e9dc79
commit 021c483a2c

View File

@ -9,7 +9,6 @@ all: corpora/$(CORPUS_NAME)/alignments.txt corpora/$(CORPUS_NAME)/src_clean.txt
clean: clean:
rm -f corpora/$(CORPUS_NAME)/*.norm
rm -f corpora/$(CORPUS_NAME)/*.lem rm -f corpora/$(CORPUS_NAME)/*.lem
rm -f corpora/$(CORPUS_NAME)/*.dict rm -f corpora/$(CORPUS_NAME)/*.dict
rm -f corpora/$(CORPUS_NAME)/src_clean.txt rm -f corpora/$(CORPUS_NAME)/src_clean.txt
@ -30,11 +29,15 @@ corpora/$(CORPUS_NAME)/src.dict:
corpora/$(CORPUS_NAME)/trg.dict: corpora/$(CORPUS_NAME)/trg.dict:
./collect_dict.py $(TRG_LANG) $(SRC_LANG) $(DICTIONARY_WEIGHT) > $@ ./collect_dict.py $(TRG_LANG) $(SRC_LANG) $(DICTIONARY_WEIGHT) > $@
corpora/$(CORPUS_NAME)/falign_result.txt: corpora/$(CORPUS_NAME)/falign_corpus.txt
./fast_align -i $< -d -o -v > $@
corpora/$(CORPUS_NAME)/src.norm corpora/$(CORPUS_NAME)/src.lem: corpora/$(CORPUS_NAME)/src.txt
corpora/$(CORPUS_NAME)/src.lem: corpora/$(CORPUS_NAME)/src.txt
./sentence_lemmatizer.py $< $(SRC_LANG) corpora/$(CORPUS_NAME)/src.norm corpora/$(CORPUS_NAME)/src.lem ./sentence_lemmatizer.py $< $(SRC_LANG) corpora/$(CORPUS_NAME)/src.norm corpora/$(CORPUS_NAME)/src.lem
corpora/$(CORPUS_NAME)/trg.norm corpora/$(CORPUS_NAME)/trg.lem: corpora/$(CORPUS_NAME)/trg.txt corpora/$(CORPUS_NAME)/trg.lem: corpora/$(CORPUS_NAME)/trg.txt
./sentence_lemmatizer.py $< $(TRG_LANG) corpora/$(CORPUS_NAME)/trg.norm corpora/$(CORPUS_NAME)/trg.lem ./sentence_lemmatizer.py $< $(TRG_LANG) corpora/$(CORPUS_NAME)/trg.norm corpora/$(CORPUS_NAME)/trg.lem
@ -42,5 +45,9 @@ corpora/$(CORPUS_NAME)/src_clean.txt corpora/$(CORPUS_NAME)/src_clean.lem corpor
./prepare_corpus.py corpora/$(CORPUS_NAME)/src.norm corpora/$(CORPUS_NAME)/trg.norm corpora/$(CORPUS_NAME)/ids.txt corpora/$(CORPUS_NAME)/src.lem corpora/$(CORPUS_NAME)/trg.lem corpora/$(CORPUS_NAME)/src.dict corpora/$(CORPUS_NAME)/trg.dict corpora/$(CORPUS_NAME)/src_clean.txt corpora/$(CORPUS_NAME)/src_clean.lem corpora/$(CORPUS_NAME)/trg_clean.txt corpora/$(CORPUS_NAME)/ids_clean.txt corpora/$(CORPUS_NAME)/falign_corpus.txt $(SRC_LANG) $(TRG_LANG) ./prepare_corpus.py corpora/$(CORPUS_NAME)/src.norm corpora/$(CORPUS_NAME)/trg.norm corpora/$(CORPUS_NAME)/ids.txt corpora/$(CORPUS_NAME)/src.lem corpora/$(CORPUS_NAME)/trg.lem corpora/$(CORPUS_NAME)/src.dict corpora/$(CORPUS_NAME)/trg.dict corpora/$(CORPUS_NAME)/src_clean.txt corpora/$(CORPUS_NAME)/src_clean.lem corpora/$(CORPUS_NAME)/trg_clean.txt corpora/$(CORPUS_NAME)/ids_clean.txt corpora/$(CORPUS_NAME)/falign_corpus.txt $(SRC_LANG) $(TRG_LANG)
corpora/$(CORPUS_NAME)/falign_result.txt: corpora/$(CORPUS_NAME)/falign_corpus.txt corpora/$(CORPUS_NAME)/trg.tok: corpora/$(CORPUS_NAME)/trg.txt
./fast_align -i $< -d -o -v > $@ /usr/local/bin/concordia-sentence-tokenizer -c /code/prod/resources/concordia-config/concordia.cfg < $< > $@
corpora/$(CORPUS_NAME)/src.tok: corpora/$(CORPUS_NAME)/src.txt
/usr/local/bin/concordia-sentence-tokenizer -c /code/prod/resources/concordia-config/concordia.cfg < $< > $@