Files
cis-benchmarks/bin/refresh_text_extracts.sh
T

24 lines
588 B
Bash

#!/usr/bin/env bash
set -euo pipefail
SCRIPT_PATH="$(readlink -f "$0")"
SCRIPT_DIR="$(dirname "$SCRIPT_PATH")"
REPO_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
PDF_DIR="$REPO_DIR/pdf"
TEXT_DIR="$REPO_DIR/text"
if ! command -v pdftotext >/dev/null 2>&1; then
echo "pdftotext is required. Install poppler-utils first." >&2
exit 1
fi
mkdir -p "$PDF_DIR" "$TEXT_DIR"
find "$PDF_DIR" -maxdepth 1 -type f -name '*.pdf' | sort | while read -r pdf; do
base="$(basename "$pdf" .pdf)"
pdftotext -layout "$pdf" "$TEXT_DIR/$base.txt"
done
echo "Refreshed text extracts under $TEXT_DIR"