228 lines
9.4 KiB
Bash
Executable File
228 lines
9.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# ============================================================
|
||
# batch-clean.sh
|
||
# Batch manga text removal (inpainting) using bubbles.json
|
||
#
|
||
# Usage:
|
||
# ./batch-clean.sh <folder>
|
||
# ./batch-clean.sh <folder> --start 3 --end 7
|
||
#
|
||
# Output per page lands in:
|
||
# <folder>/translated/<page_stem>/
|
||
# └── <page_stem>_cleaned.png
|
||
# ============================================================
|
||
|
||
set -uo pipefail
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# CONFIGURATION
|
||
# ─────────────────────────────────────────────────────────────
|
||
START_PAGE=1
|
||
END_PAGE=999999
|
||
PYTHON_BIN="python"
|
||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||
CLEANER="${SCRIPT_DIR}/clean_bubbles.py"
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# COLOURS
|
||
# ─────────────────────────────────────────────────────────────
|
||
RED='\033[0;31m'
|
||
GREEN='\033[0;32m'
|
||
YELLOW='\033[1;33m'
|
||
CYAN='\033[0;36m'
|
||
BOLD='\033[1m'
|
||
RESET='\033[0m'
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# HELPERS
|
||
# ─────────────────────────────────────────────────────────────
|
||
usage() {
|
||
echo ""
|
||
echo -e "${BOLD}Usage:${RESET}"
|
||
echo " $0 <folder> [options]"
|
||
echo ""
|
||
echo -e "${BOLD}Options:${RESET}"
|
||
echo " --start First page number (default: 1)"
|
||
echo " --end Last page number (default: all)"
|
||
echo " --python Python binary (default: python)"
|
||
echo " --help, -h Show this help"
|
||
echo ""
|
||
echo -e "${BOLD}Examples:${RESET}"
|
||
echo " $0 pages-for-tests"
|
||
echo " $0 pages-for-tests --start 3 --end 7"
|
||
echo ""
|
||
}
|
||
|
||
log_info() { echo -e "${CYAN}ℹ️ $*${RESET}"; }
|
||
log_ok() { echo -e "${GREEN}✅ $*${RESET}"; }
|
||
log_warn() { echo -e "${YELLOW}⚠️ $*${RESET}"; }
|
||
log_error() { echo -e "${RED}❌ $*${RESET}"; }
|
||
log_section() {
|
||
echo -e "\n${BOLD}${CYAN}══════════════════════════════════════════${RESET}"
|
||
echo -e "${BOLD}${CYAN} 🧹 $*${RESET}"
|
||
echo -e "${BOLD}${CYAN}══════════════════════════════════════════${RESET}"
|
||
}
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# ARGUMENT PARSING
|
||
# ─────────────────────────────────────────────────────────────
|
||
if [[ $# -eq 0 ]]; then
|
||
log_error "No folder specified."
|
||
usage
|
||
exit 1
|
||
fi
|
||
|
||
FOLDER="$1"
|
||
shift
|
||
|
||
while [[ $# -gt 0 ]]; do
|
||
case "$1" in
|
||
--start) START_PAGE="$2"; shift 2 ;;
|
||
--end) END_PAGE="$2"; shift 2 ;;
|
||
--python) PYTHON_BIN="$2"; shift 2 ;;
|
||
--help|-h) usage; exit 0 ;;
|
||
*)
|
||
log_error "Unknown option: $1"
|
||
usage
|
||
exit 1
|
||
;;
|
||
esac
|
||
done
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# VALIDATION
|
||
# ─────────────────────────────────────────────────────────────
|
||
if [[ ! -d "$FOLDER" ]]; then
|
||
log_error "Folder not found: $FOLDER"
|
||
exit 1
|
||
fi
|
||
|
||
if [[ ! -f "$CLEANER" ]]; then
|
||
log_error "clean_bubbles.py not found at: $CLEANER"
|
||
exit 1
|
||
fi
|
||
|
||
if ! command -v "$PYTHON_BIN" &>/dev/null; then
|
||
log_error "Python binary not found: $PYTHON_BIN"
|
||
log_error "Try --python python3"
|
||
exit 1
|
||
fi
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# DISCOVER IMAGES
|
||
# ─────────────────────────────────────────────────────────────
|
||
ALL_IMAGES=()
|
||
while IFS= read -r -d '' img; do
|
||
ALL_IMAGES+=("$img")
|
||
done < <(
|
||
find "$FOLDER" -maxdepth 1 -type f \
|
||
\( -iname "*.jpg" -o -iname "*.jpeg" \
|
||
-o -iname "*.png" -o -iname "*.webp" \) \
|
||
-print0 | sort -z
|
||
)
|
||
|
||
TOTAL=${#ALL_IMAGES[@]}
|
||
|
||
if [[ $TOTAL -eq 0 ]]; then
|
||
log_error "No image files found in: $FOLDER"
|
||
exit 1
|
||
fi
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# SLICE TO REQUESTED PAGE RANGE
|
||
# ─────────────────────────────────────────────────────────────
|
||
PAGES=()
|
||
for i in "${!ALL_IMAGES[@]}"; do
|
||
PAGE_NUM=$(( i + 1 ))
|
||
if [[ $PAGE_NUM -ge $START_PAGE && $PAGE_NUM -le $END_PAGE ]]; then
|
||
PAGES+=("${ALL_IMAGES[$i]}")
|
||
fi
|
||
done
|
||
|
||
if [[ ${#PAGES[@]} -eq 0 ]]; then
|
||
log_error "No pages in range [${START_PAGE}, ${END_PAGE}] (total: ${TOTAL})"
|
||
exit 1
|
||
fi
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# SUMMARY HEADER
|
||
# ─────────────────────────────────────────────────────────────
|
||
log_section "BATCH MANGA CLEANER"
|
||
log_info "📂 Folder : $(realpath "$FOLDER")"
|
||
log_info "📄 Pages : ${#PAGES[@]} of ${TOTAL} total"
|
||
log_info "🔢 Range : ${START_PAGE} → ${END_PAGE}"
|
||
echo ""
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# PROCESS EACH PAGE
|
||
# ─────────────────────────────────────────────────────────────
|
||
PASS=0
|
||
FAIL=0
|
||
FAIL_LIST=()
|
||
|
||
for i in "${!PAGES[@]}"; do
|
||
IMAGE="${PAGES[$i]}"
|
||
PAGE_NUM=$(( START_PAGE + i ))
|
||
STEM="$(basename "${IMAGE%.*}")"
|
||
WORKDIR="${FOLDER}/translated/${STEM}"
|
||
|
||
echo ""
|
||
echo -e "${BOLD}──────────────────────────────────────────${RESET}"
|
||
echo -e "${BOLD} 🖼️ [${PAGE_NUM}/${TOTAL}] ${STEM}${RESET}"
|
||
echo -e "${BOLD}──────────────────────────────────────────${RESET}"
|
||
|
||
OUTPUT_JSON="${WORKDIR}/bubbles.json"
|
||
OUTPUT_CLEANED="${WORKDIR}/${STEM}_cleaned.png"
|
||
|
||
if [[ ! -f "$OUTPUT_JSON" ]]; then
|
||
log_warn "Skipping: bubbles.json not found in ${WORKDIR}"
|
||
FAIL=$(( FAIL + 1 ))
|
||
FAIL_LIST+=("${STEM} (No JSON)")
|
||
continue
|
||
fi
|
||
|
||
log_info "🗂️ Image : $(basename "$IMAGE")"
|
||
log_info "🧹 Cleaning text..."
|
||
|
||
# ── Run the cleaner ───────────────────────────────────────
|
||
if "$PYTHON_BIN" "$CLEANER" \
|
||
-i "$IMAGE" \
|
||
-j "$OUTPUT_JSON" \
|
||
-o "$OUTPUT_CLEANED"; then
|
||
|
||
if [[ -f "$OUTPUT_CLEANED" ]]; then
|
||
log_ok "Cleaned image saved → ${STEM}_cleaned.png"
|
||
PASS=$(( PASS + 1 ))
|
||
else
|
||
log_error "Script ran but output image is missing."
|
||
FAIL=$(( FAIL + 1 ))
|
||
FAIL_LIST+=("${STEM} (Missing Output)")
|
||
fi
|
||
else
|
||
log_error "Page ${PAGE_NUM} FAILED — check output above."
|
||
FAIL=$(( FAIL + 1 ))
|
||
FAIL_LIST+=("${STEM} (Script Error)")
|
||
fi
|
||
|
||
done
|
||
|
||
# ─────────────────────────────────────────────────────────────
|
||
# FINAL SUMMARY
|
||
# ─────────────────────────────────────────────────────────────
|
||
log_section "BATCH CLEANING COMPLETE"
|
||
echo -e " ✅ ${GREEN}Passed : ${PASS}${RESET}"
|
||
echo -e " ❌ ${RED}Failed : ${FAIL}${RESET}"
|
||
|
||
if [[ ${#FAIL_LIST[@]} -gt 0 ]]; then
|
||
echo ""
|
||
log_warn "Failed pages:"
|
||
for NAME in "${FAIL_LIST[@]}"; do
|
||
echo -e " ❌ ${RED}${NAME}${RESET}"
|
||
done
|
||
fi
|
||
|
||
echo ""
|
||
log_info "📦 Output folder: $(realpath "${FOLDER}/translated")"
|
||
echo ""
|
||
|
||
[[ $FAIL -eq 0 ]] && exit 0 || exit 1 |