blob: 5ce8b08833e7415a4b19a3917f897089abdd0943 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
|
#!/usr/bin/env sh
# OCR a screen region (default) or an image file → clipboard.
#
# Usage:
# ocr # interactive: select a region with slurp, OCR it
# ocr <file> # OCR an image file
#
# Requires: tesseract (+tesseract-data-eng, tesseract-data-por),
# grim, slurp, wl-clipboard, libnotify.
#
# Override languages via TESSERACT_LANG (e.g. TESSERACT_LANG=eng).
set -eu
lang="${TESSERACT_LANG:-eng+por}"
if [ "${1:-}" ]; then
[ -r "$1" ] || {
notify-send -u critical "📋 OCR" "Cannot read: $1"
exit 1
}
text="$(tesseract "$1" - -l "$lang" 2>/dev/null || true)"
else
region="$(slurp 2>/dev/null)" || exit 0
text="$(grim -g "$region" - | tesseract - - -l "$lang" 2>/dev/null || true)"
fi
# Trim trailing whitespace per line; collapse runs of blank lines; drop
# leading blanks.
text="$(printf '%s\n' "$text" | awk '
{ sub(/[[:space:]]+$/, "") }
NF { print; blank = 0; next }
!blank { print; blank = 1 }
' | sed -e '/./,$!d')"
if [ -z "$text" ]; then
notify-send -u low "📋 OCR" "No text detected."
exit 1
fi
printf '%s' "$text" | wl-copy
notify-send -t 3000 "📋 OCR copied" "$(printf '%s' "$text" | head -c 200)"
|
