added nautilus scripts (needs nautilus-python package)

This commit is contained in:
2026-06-14 18:55:25 +02:00
parent 33df2d0d81
commit dd4af575b5
247 changed files with 14784 additions and 0 deletions
@@ -0,0 +1,41 @@
#!/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=""
# Execute initial checks.
_check_dependencies "
command=pdffonts; pkg_manager=apt; package=poppler-utils |
command=pdffonts; pkg_manager=dnf; package=poppler-utils |
command=pdffonts; pkg_manager=pacman; package=poppler |
command=pdffonts; pkg_manager=zypper; package=poppler-tools"
_display_wait_box "2"
input_files=$(_get_files "par_type=file; par_recursive=true; par_get_pwd=true; par_select_mime=application/pdf")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" ""
local std_output=""
std_output=$(_storage_text_read_all)
std_output=$(_text_sort "$std_output")
_display_list_box "$std_output" "--column=File"
}
_main_task() {
local input_file=$1
local output_dir=$2
local temp_file=""
# Save the result only for 'without fonts' PDFs.
if ! pdffonts "$input_file" | sed -n 3p | grep --quiet "."; then
_storage_text_write_ln "$(_text_remove_pwd "$input_file")"
fi
}
_main "$@"
@@ -0,0 +1,41 @@
#!/usr/bin/env bash
# Source the script 'common-functions.sh'.
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
ROOT_DIR=$(grep --only-matching "^.*scripts[^/]*" <<<"$SCRIPT_DIR")
source "$ROOT_DIR/common-functions.sh"
_main() {
local input_files=""
local output_dir=""
# Execute initial checks.
TEMP_DATA_TASK="eng"
_check_dependencies "
command=ocrmypdf |
pkg_manager=apt; package=tesseract-ocr-$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=application/pdf")
output_dir=$(_get_output_dir "par_use_same_dir=false")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" "$output_dir"
_display_result_box "$output_dir"
}
_main_task() {
local input_file=$1
local output_dir=$2
local output_file=""
local std_output=""
# Run the main process.
output_file=$(_get_output_filename "$input_file" "$output_dir" "par_extension_opt=preserve")
std_output=$(ocrmypdf --l "$TEMP_DATA_TASK" --output-type pdfa --skip-text --jobs "$(_get_max_procs)" -- "$input_file" "$output_file" 2>&1)
_check_output "$?" "$std_output" "$input_file" "" || return 1
}
_main "$@"
@@ -0,0 +1,41 @@
#!/usr/bin/env bash
# Source the script 'common-functions.sh'.
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
ROOT_DIR=$(grep --only-matching "^.*scripts[^/]*" <<<"$SCRIPT_DIR")
source "$ROOT_DIR/common-functions.sh"
_main() {
local input_files=""
local output_dir=""
# Execute initial checks.
TEMP_DATA_TASK="fra"
_check_dependencies "
command=ocrmypdf |
pkg_manager=apt; package=tesseract-ocr-$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=application/pdf")
output_dir=$(_get_output_dir "par_use_same_dir=false")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" "$output_dir"
_display_result_box "$output_dir"
}
_main_task() {
local input_file=$1
local output_dir=$2
local output_file=""
local std_output=""
# Run the main process.
output_file=$(_get_output_filename "$input_file" "$output_dir" "par_extension_opt=preserve")
std_output=$(ocrmypdf --l "$TEMP_DATA_TASK" --output-type pdfa --skip-text --jobs "$(_get_max_procs)" -- "$input_file" "$output_file" 2>&1)
_check_output "$?" "$std_output" "$input_file" "" || return 1
}
_main "$@"
@@ -0,0 +1,41 @@
#!/usr/bin/env bash
# Source the script 'common-functions.sh'.
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
ROOT_DIR=$(grep --only-matching "^.*scripts[^/]*" <<<"$SCRIPT_DIR")
source "$ROOT_DIR/common-functions.sh"
_main() {
local input_files=""
local output_dir=""
# Execute initial checks.
TEMP_DATA_TASK="deu"
_check_dependencies "
command=ocrmypdf |
pkg_manager=apt; package=tesseract-ocr-$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=application/pdf")
output_dir=$(_get_output_dir "par_use_same_dir=false")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" "$output_dir"
_display_result_box "$output_dir"
}
_main_task() {
local input_file=$1
local output_dir=$2
local output_file=""
local std_output=""
# Run the main process.
output_file=$(_get_output_filename "$input_file" "$output_dir" "par_extension_opt=preserve")
std_output=$(ocrmypdf --l "$TEMP_DATA_TASK" --output-type pdfa --skip-text --jobs "$(_get_max_procs)" -- "$input_file" "$output_file" 2>&1)
_check_output "$?" "$std_output" "$input_file" "" || return 1
}
_main "$@"
@@ -0,0 +1,41 @@
#!/usr/bin/env bash
# Source the script 'common-functions.sh'.
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
ROOT_DIR=$(grep --only-matching "^.*scripts[^/]*" <<<"$SCRIPT_DIR")
source "$ROOT_DIR/common-functions.sh"
_main() {
local input_files=""
local output_dir=""
# Execute initial checks.
TEMP_DATA_TASK="ita"
_check_dependencies "
command=ocrmypdf |
pkg_manager=apt; package=tesseract-ocr-$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=application/pdf")
output_dir=$(_get_output_dir "par_use_same_dir=false")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" "$output_dir"
_display_result_box "$output_dir"
}
_main_task() {
local input_file=$1
local output_dir=$2
local output_file=""
local std_output=""
# Run the main process.
output_file=$(_get_output_filename "$input_file" "$output_dir" "par_extension_opt=preserve")
std_output=$(ocrmypdf --l "$TEMP_DATA_TASK" --output-type pdfa --skip-text --jobs "$(_get_max_procs)" -- "$input_file" "$output_file" 2>&1)
_check_output "$?" "$std_output" "$input_file" "" || return 1
}
_main "$@"
@@ -0,0 +1,41 @@
#!/usr/bin/env bash
# Source the script 'common-functions.sh'.
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
ROOT_DIR=$(grep --only-matching "^.*scripts[^/]*" <<<"$SCRIPT_DIR")
source "$ROOT_DIR/common-functions.sh"
_main() {
local input_files=""
local output_dir=""
# Execute initial checks.
TEMP_DATA_TASK="por"
_check_dependencies "
command=ocrmypdf |
pkg_manager=apt; package=tesseract-ocr-$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=application/pdf")
output_dir=$(_get_output_dir "par_use_same_dir=false")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" "$output_dir"
_display_result_box "$output_dir"
}
_main_task() {
local input_file=$1
local output_dir=$2
local output_file=""
local std_output=""
# Run the main process.
output_file=$(_get_output_filename "$input_file" "$output_dir" "par_extension_opt=preserve")
std_output=$(ocrmypdf --l "$TEMP_DATA_TASK" --output-type pdfa --skip-text --jobs "$(_get_max_procs)" -- "$input_file" "$output_file" 2>&1)
_check_output "$?" "$std_output" "$input_file" "" || return 1
}
_main "$@"
@@ -0,0 +1,41 @@
#!/usr/bin/env bash
# Source the script 'common-functions.sh'.
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
ROOT_DIR=$(grep --only-matching "^.*scripts[^/]*" <<<"$SCRIPT_DIR")
source "$ROOT_DIR/common-functions.sh"
_main() {
local input_files=""
local output_dir=""
# Execute initial checks.
TEMP_DATA_TASK="rus"
_check_dependencies "
command=ocrmypdf |
pkg_manager=apt; package=tesseract-ocr-$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=application/pdf")
output_dir=$(_get_output_dir "par_use_same_dir=false")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" "$output_dir"
_display_result_box "$output_dir"
}
_main_task() {
local input_file=$1
local output_dir=$2
local output_file=""
local std_output=""
# Run the main process.
output_file=$(_get_output_filename "$input_file" "$output_dir" "par_extension_opt=preserve")
std_output=$(ocrmypdf --l "$TEMP_DATA_TASK" --output-type pdfa --skip-text --jobs "$(_get_max_procs)" -- "$input_file" "$output_file" 2>&1)
_check_output "$?" "$std_output" "$input_file" "" || return 1
}
_main "$@"
@@ -0,0 +1,41 @@
#!/usr/bin/env bash
# Source the script 'common-functions.sh'.
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
ROOT_DIR=$(grep --only-matching "^.*scripts[^/]*" <<<"$SCRIPT_DIR")
source "$ROOT_DIR/common-functions.sh"
_main() {
local input_files=""
local output_dir=""
# Execute initial checks.
TEMP_DATA_TASK="spa"
_check_dependencies "
command=ocrmypdf |
pkg_manager=apt; package=tesseract-ocr-$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=application/pdf")
output_dir=$(_get_output_dir "par_use_same_dir=false")
# Execute the function '_main_task' for each file in parallel.
_run_task_parallel "$input_files" "$output_dir"
_display_result_box "$output_dir"
}
_main_task() {
local input_file=$1
local output_dir=$2
local output_file=""
local std_output=""
# Run the main process.
output_file=$(_get_output_filename "$input_file" "$output_dir" "par_extension_opt=preserve")
std_output=$(ocrmypdf --l "$TEMP_DATA_TASK" --output-type pdfa --skip-text --jobs "$(_get_max_procs)" -- "$input_file" "$output_file" 2>&1)
_check_output "$?" "$std_output" "$input_file" "" || return 1
}
_main "$@"