From ef97ce0e55410c48c22ca6d06da1ceae4f836b96 Mon Sep 17 00:00:00 2001 From: AuroraWright Date: Sat, 2 Mar 2024 09:33:39 +0100 Subject: [PATCH] Prepare for new version --- README.md | 5 +++-- owocr_config.ini | 2 +- setup.py | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index a0e7afa..88677ef 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@ Command line client for several Japanese OCR providers derived from [Manga OCR]( # Installation -This has been tested with Python 3.11. Newer/older versions might work. It can be installed with `pip install owocr` +This has been tested with Python 3.11 and 3.12. Newer/older versions might work. It can be installed with `pip install owocr` # Usage @@ -13,7 +13,8 @@ Basic usage is comparable to Manga OCR as in, `owocr` keeps scanning for images Additionally: - Scanning the clipboard takes basically zero system resources on macOS and Windows - Supports reading images and/or writing text to a websocket with the `-r=websocket` and/or `-w=websocket` parameters (the port is 7331 by default, and is configurable in the config file) -- Supports capturing the screen directly with `-r screencapture`. It will default to the entire first screen every 3 seconds, but a different screen/screen coordinates/window/delay can be specified in the config file. Instead of using a delay between screenshots you can also specify a keyboard combo (refer to the config file or the help page) +- Supports reading images from a Unix domain socket (`/tmp/owocr.sock`) on macOS and Linux with `-r=unixsocket` +- Supports capturing the screen directly with `-r=screencapture`. It will default to the entire first screen every 3 seconds, but a different screen/screen coordinates/window/delay can be specified in the config file. Instead of using a delay between screenshots you can also specify a keyboard combo (refer to the config file or the help page) - You can pause/unpause the image processing by pressing "p" or terminate the script with "t" or "q" inside the terminal window - You can switch between OCR providers pressing their corresponding keyboard key inside the terminal window (refer to the list of keys in the providers list below) - You can start the script paused with the `-p` option or with a specific provider with the `-e` option (refer to `owocr -h` for the list) diff --git a/owocr_config.ini b/owocr_config.ini index b6ae588..47dc493 100644 --- a/owocr_config.ini +++ b/owocr_config.ini @@ -20,7 +20,7 @@ ;screen_capture_coords = ;screen_capture_coords = 400,200,1500,600 ;screen_capture_coords = OBS -;note: if screen_capture_coords is a window name, this can be changed to capture inactive windows too. In that case, make sure the window is not covered by other windows! +;note: if screen_capture_coords is a window name, this can be changed to capture inactive windows too. On Linux, the window must then not be covered by other windows! ;screen_capture_only_active_windows = True ;screen_capture_delay_secs = 3 ;note: this specifies a combo to wait on for taking a screenshot instead of using the delay. As an example: ++s. The list of keys can be found here: https://pynput.readthedocs.io/en/latest/keyboard.html#pynput.keyboard.Key diff --git a/setup.py b/setup.py index 1d63aa6..2855dcc 100644 --- a/setup.py +++ b/setup.py @@ -5,7 +5,7 @@ long_description = (Path(__file__).parent / "README.md").read_text('utf-8') setup( name="owocr", - version='1.6', + version='1.7', description="Japanese OCR", long_description=long_description, long_description_content_type="text/markdown",