rjawor/concordia-server
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

clean-filtering option

Browse Source
This commit is contained in:
rjawor 2017-07-21 17:55:28 +02:00
parent 545463ad9c
commit a5eda01b39
1 changed files with 17 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
mgiza-aligner/corpus-compilator/Makefile
View File

@ -10,15 +10,17 @@ all: corpora/$(CORPUS_NAME)/src_filtered.txt corpora/$(CORPUS_NAME)/trg_filtered
corpora/$(CORPUS_NAME)/src_filtered.txt corpora/$(CORPUS_NAME)/trg_filtered.txt: corpora/$(CORPUS_NAME)/src_clean.txt corpora/$(CORPUS_NAME)/trg_clean.txt corpora/$(CORPUS_NAME)/corpus_lines.txt corpora/$(CORPUS_NAME)/src_filtered.txt corpora/$(CORPUS_NAME)/trg_filtered.txt: corpora/$(CORPUS_NAME)/src_clean.txt corpora/$(CORPUS_NAME)/trg_clean.txt corpora/$(CORPUS_NAME)/corpus_lines.txt
./compile.py corpora/$(CORPUS_NAME)/src_clean.txt corpora/$(CORPUS_NAME)/trg_clean.txt corpora/$(CORPUS_NAME)/corpus_lines.txt corpora/$(CORPUS_NAME)/src_filtered.txt corpora/$(CORPUS_NAME)/trg_filtered.txt ./compile.py corpora/$(CORPUS_NAME)/src_clean.txt corpora/$(CORPUS_NAME)/trg_clean.txt corpora/$(CORPUS_NAME)/corpus_lines.txt corpora/$(CORPUS_NAME)/src_filtered.txt corpora/$(CORPUS_NAME)/trg_filtered.txt
corpora/$(CORPUS_NAME)/corpus_lines.txt: index-corpus dictionaries/$(DICTIONARY_NAME).lem corpora/$(CORPUS_NAME)/corpus_lines.txt: corpora/$(CORPUS_NAME)/corpus.indexed dictionaries/$(DICTIONARY_NAME).lem
./get_corpus_lines.py dictionaries/$(DICTIONARY_NAME).lem corpora/$(CORPUS_NAME)/report.txt > $@ ./get_corpus_lines.py dictionaries/$(DICTIONARY_NAME).lem corpora/$(CORPUS_NAME)/report.txt > $@
index-corpus: split-corpus corpora/$(CORPUS_NAME)/corpus.indexed: corpora/$(CORPUS_NAME)/corpus.split
./load_corpus.sh corpora/$(CORPUS_NAME)/csv/ ./load_corpus.sh corpora/$(CORPUS_NAME)/csv/
touch corpora/$(CORPUS_NAME)/corpus.indexed
split-corpus: corpora/$(CORPUS_NAME)/src.csv corpora/$(CORPUS_NAME)/corpus.split: corpora/$(CORPUS_NAME)/src.csv
mkdir corpora/$(CORPUS_NAME)/csv mkdir corpora/$(CORPUS_NAME)/csv
split -l $(CORPUS_CHUNK_SIZE) -d --additional-suffix=".csv" $< corpora/$(CORPUS_NAME)/csv/src split -l $(CORPUS_CHUNK_SIZE) -d --additional-suffix=".csv" $< corpora/$(CORPUS_NAME)/csv/src
touch corpora/$(CORPUS_NAME)/corpus.split
corpora/$(CORPUS_NAME)/src.csv: corpora/$(CORPUS_NAME)/src_clean.lem corpora/$(CORPUS_NAME)/src.csv: corpora/$(CORPUS_NAME)/src_clean.lem
./lem2csv.py $< > $@ ./lem2csv.py $< > $@
@ -42,7 +44,19 @@ corpora/$(CORPUS_NAME)/trg.tok: corpora/$(CORPUS_NAME)/trg.txt
corpora/$(CORPUS_NAME)/src.tok: corpora/$(CORPUS_NAME)/src.txt corpora/$(CORPUS_NAME)/src.tok: corpora/$(CORPUS_NAME)/src.txt
/usr/local/bin/concordia-sentence-tokenizer -c ../../concordia.cfg < $< > $@ /usr/local/bin/concordia-sentence-tokenizer -c ../../concordia.cfg < $< > $@
clean-filtering:
rm -f corpora/$(CORPUS_NAME)/src_filtered.txt
rm -f corpora/$(CORPUS_NAME)/trg_filtered.txt
rm -f corpora/$(CORPUS_NAME)/corpus_lines.txt
rm -f corpora/$(CORPUS_NAME)/report.txt
rm -f dictionaries/$(DICTIONARY_NAME).lem
clean: clean:
rm -f corpora/$(CORPUS_NAME)/src_filtered.txt
rm -f corpora/$(CORPUS_NAME)/trg_filtered.txt
rm -f corpora/$(CORPUS_NAME)/corpus.indexed
rm -f corpora/$(CORPUS_NAME)/corpus.split
rm -f corpora/$(CORPUS_NAME)/report.txt rm -f corpora/$(CORPUS_NAME)/report.txt
./clear_solr_index.sh ./clear_solr_index.sh
rm -rf corpora/$(CORPUS_NAME)/csv rm -rf corpora/$(CORPUS_NAME)/csv