From 79688623421bef6a9c1db39e8700657bb45311a9 Mon Sep 17 00:00:00 2001 From: Tokuhiro Matsuno Date: Mon, 5 Aug 2024 22:46:15 +0900 Subject: [PATCH] Use bunzip2 in streaming style do not save the bzipped file on the disk. github action doesnt have enough disk. --- Makefile | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/Makefile b/Makefile index a167f03..2e1c941 100644 --- a/Makefile +++ b/Makefile @@ -12,11 +12,8 @@ test: autopep8 --max-line-length 180 -i *.py */*.py flake8 . --count --exit-zero --max-complexity=30 --max-line-length=1200 --statistics -dat/jawiki-latest-pages-articles.xml.bz2: - wget --no-verbose --no-clobber -O dat/jawiki-latest-pages-articles.xml.bz2 https://dumps.wikimedia.org/jawiki/latest/jawiki-latest-pages-articles.xml.bz2 - -dat/jawiki-latest-pages-articles.xml: dat/jawiki-latest-pages-articles.xml.bz2 - bunzip2 --keep --force dat/jawiki-latest-pages-articles.xml.bz2 +dat/jawiki-latest-pages-articles.xml: + curl -s https://dumps.wikimedia.org/jawiki/latest/jawiki-latest-pages-articles.xml.bz2 | bunzip2 > dat/jawiki-latest-pages-articles.xml dat/grepped.txt: dat/jawiki-latest-pages-articles.xml grep -E ".*|'''[』|((]" dat/jawiki-latest-pages-articles.xml > dat/grepped.txt