Files
dotfiles/.local/share/nautilus/scripts/Image/Text recognition (OCR)/Image OCR (in Italian)
T

51 lines
1.7 KiB
Bash
Executable File

#!/usr/bin/env bash
# Source the script 'common-functions.sh'.
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
ROOT_DIR=$(grep --only-matching "^.*scripts[^/]*" <<<"$SCRIPT_DIR")
source "$ROOT_DIR/common-functions.sh"
_main() {
local input_files=""
local output_dir=""
# Execute initial checks.
TEMP_DATA_TASK="ita"
_check_dependencies "
pkg_manager=apt; package=tesseract-ocr-$TEMP_DATA_TASK |
pkg_manager=dnf; package=tesseract-langpack-$TEMP_DATA_TASK |
pkg_manager=pacman; package=tesseract-data-$TEMP_DATA_TASK |
pkg_manager=zypper; package=tesseract-ocr-traineddata-$TEMP_DATA_TASK"
_display_wait_box "2"
input_files=$(_get_files "par_type=file; par_select_mime=image/; par_validate_conflict=true")
output_dir=$(_get_output_dir "par_use_same_dir=true")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" "$output_dir"
_display_result_box "$output_dir"
}
_main_task() {
local input_file=$1
local output_dir=$2
local output_file=""
local std_output=""
local temp_file=""
# Work on a temporary file.
temp_file=$(_get_temp_file)
# Run the main process.
std_output=$(tesseract "$input_file" "$temp_file" -l "$TEMP_DATA_TASK" 2>&1)
_check_output "$?" "$std_output" "$input_file" "$temp_file.txt" || return 1
# Move the temporary file to the output.
output_file=$(_get_output_filename "$input_file" "$output_dir" "par_extension_opt=replace; par_extension=txt")
_move_temp_file_to_output "$input_file" "$temp_file.txt" "$output_file"
# Remove the temporary files on each iteration (if not removed before).
rm -f -- "$temp_file"
}
_main "$@"