From 62e6777952716e2ba1d100ca6700180b27433548 Mon Sep 17 00:00:00 2001 From: Nirant K Date: Wed, 14 Nov 2018 15:53:59 +0000 Subject: [PATCH] Add download and unzip script --- ulmfit/xnli/prepare_xnli.sh | 48 +++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 ulmfit/xnli/prepare_xnli.sh diff --git a/ulmfit/xnli/prepare_xnli.sh b/ulmfit/xnli/prepare_xnli.sh new file mode 100644 index 0000000..31e1f0b --- /dev/null +++ b/ulmfit/xnli/prepare_xnli.sh @@ -0,0 +1,48 @@ +#!/usr/bin/env bash +# Script to download a Wikipedia dump + +# Script is partially based on https://github.com/facebookresearch/fastText/blob/master/get-wikimedia.sh +ROOT="data" +DUMP_DIR="${ROOT}/xnli_dnld" +EXTR_DIR="${ROOT}/xnli_extr" +WIKI_DIR="${ROOT}/xnli" +EXTR="wikiextractor" +mkdir -p "${ROOT}" +mkdir -p "${DUMP_DIR}" +mkdir -p "${WIKI_DIR}" + +echo "Saving data in ""$ROOT" +read -r -p "Choose a language (e.g. en, fr, etc.): " choice +LANG="$choice" +echo "Chosen language: ""$LANG" +MT_FILE="XNLI-MT-1.0.zip" +XNLI_FILE="XNLI-1.0.zip" +MT_PATH="${DUMP_DIR}/${MT_FILE}" +XNLI_PATH="${DUMP_DIR}/${XNLI_FILE}" + +if [ ! -f "${MT_PATH}" ]; then + read -r -p "Continue to download (WARNING: This might be big and can take a long time!) (y/n)? " choice + case "$choice" in + y|Y ) echo "Starting download...";; + n|N ) echo "Exiting";exit 1;; + * ) echo "Invalid answer";exit 1;; + esac + wget -c "https://s3.amazonaws.com/xnli/XNLI-MT-1.0.zip" -P "${DUMP_DIR}" + wget -c "https://s3.amazonaws.com/xnli/XNLI-1.0.zip" -P "${DUMP_DIR}" + +else + echo "${MT_PATH} already exists. Skipping download." +fi + +if [ ! -d "${EXTR_DIR}" ]; then + read -r -p "Continue to extract XNLI (WARNING: This might take a long time!) (y/n)? " choice + case "$choice" in + y|Y ) echo "Extracting ${MT_PATH} to ${EXTR_DIR}...";; + n|N ) echo "Exiting";exit 1;; + * ) echo "Invalid answer";exit 1;; + esac + unzip "${MT_PATH}" -d "${EXTR_DIR}" + unzip "${XNLI_PATH}" -d "${EXTR_DIR}" +else + echo "${EXTR_DIR} already exists. Skipping extraction." +fi