GameSentenceMiner 2.12.0.dev2__tar.gz → 2.12.0.dev3__tar.gz

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/GameSentenceMiner/config_gui.py

@@ -114,7 +114,7 @@ class ConfigApp:
         self.window.protocol("WM_DELETE_WINDOW", self.hide)
         self.obs_scene_listbox_changed = False
 
-        self.window.geometry("800x700")
+        # self.window.geometry("800x500")
         self.current_row = 0
 
         self.master_config: Config = configuration.load_config()
@@ -137,6 +137,7 @@ class ConfigApp:
         self.profiles_tab = None
         self.ai_tab = None
         self.advanced_tab = None
+        self.wip_tab = None
 
         self.create_tabs()
 
@@ -158,6 +159,8 @@ class ConfigApp:
                             "Saves Settings and Syncs CHANGED SETTINGS to all profiles.", row=0,
                             column=2)
 
+        self.window.update_idletasks()
+        self.window.geometry("")
         self.window.withdraw()
 
     def create_tabs(self):
@@ -172,6 +175,7 @@ class ConfigApp:
         self.create_profiles_tab()
         self.create_ai_tab()
         self.create_advanced_tab()
+        self.create_wip_tab()
 
     def add_reset_button(self, frame, category, row, column=0, recreate_tab=None):
         """
@@ -230,6 +234,7 @@ class ConfigApp:
         if self.window is not None:
             self.window.deiconify()
             self.window.lift()
+            self.window.update_idletasks()
             return
 
     def hide(self):
@@ -250,7 +255,8 @@ class ConfigApp:
                 open_multimine_on_startup=self.open_multimine_on_startup.get(),
                 texthook_replacement_regex=self.texthook_replacement_regex.get(),
                 use_both_clipboard_and_websocket=self.use_both_clipboard_and_websocket.get(),
-                texthooker_port=int(self.texthooker_port.get())
+                texthooker_port=int(self.texthooker_port.get()),
+                native_language=CommonLanguages.from_name(self.native_language.get()) if self.native_language.get() else CommonLanguages.ENGLISH.value,
             ),
             paths=Paths(
                 folder_to_watch=self.folder_to_watch.get(),
@@ -362,6 +368,10 @@ class ConfigApp:
                 use_canned_context_prompt=self.use_canned_context_prompt.get(),
                 custom_prompt=self.custom_prompt.get("1.0", tk.END),
                 dialogue_context_length=int(self.ai_dialogue_context_length.get()),
+            ),
+            wip=WIP(
+                overlay_websocket_port=int(self.overlay_websocket_port.get()),
+                overlay_websocket_send=self.overlay_websocket_send.get()
             )
         )
 
@@ -547,6 +557,15 @@ class ConfigApp:
         self.latest_version = ttk.Label(self.general_tab, text=get_latest_version(), bootstyle="secondary")
         self.latest_version.grid(row=self.current_row, column=1, sticky='W', pady=2)
         self.current_row += 1
+        
+        # Native Language Selection
+        HoverInfoLabelWidget(self.general_tab, text="Native Language:",
+                             tooltip="Select your native language. This is used for various features, but will not change the look of GSM.",
+                                row=self.current_row, column=0)
+        self.native_language = ttk.Combobox(self.general_tab, values=CommonLanguages.get_all_names_pretty(), state="readonly")
+        self.native_language.set(CommonLanguages.from_code(self.settings.general.native_language).name.replace('_', ' ').title())
+        self.native_language.grid(row=self.current_row, column=1, sticky='EW', pady=2)
+        self.current_row += 1
 
         ttk.Label(self.general_tab, text="Indicates important/required settings.", foreground="dark orange",
                   font=("Helvetica", 10, "bold")).grid(row=self.current_row, column=0, columnspan=2, sticky='W', pady=2)
@@ -1674,6 +1693,54 @@ class ConfigApp:
     #
     #
     #     help_frame.grid_columnconfigure(0, weight=1)
+    
+    @new_tab
+    def create_wip_tab(self):
+        if self.wip_tab is None:
+            self.wip_tab = ttk.Frame(self.notebook, padding=15)
+            self.notebook.add(self.wip_tab, text='WIP')
+        else:
+            for widget in self.wip_tab.winfo_children():
+                widget.destroy()
+
+        wip_frame = self.wip_tab
+
+        ttk.Label(wip_frame, text="Warning: These features are experimental and may not work as expected.",
+                  foreground="red", font=("Helvetica", 10, "bold")).grid(row=self.current_row, column=0, columnspan=2,
+                                                                       sticky='W', pady=5)
+                  
+        self.current_row += 1
+        
+        ttk.Label(wip_frame, text="Overlay requires OwOCR dependencies to be installed, and requires an external app to be running.",
+                  foreground="red", font=("Helvetica", 10, "bold")).grid(row=self.current_row, column=0, columnspan=2,
+                                                                       sticky='W', pady=5)
+                  
+        self.current_row += 1
+
+        HoverInfoLabelWidget(wip_frame, text="Overlay WebSocket Port:",
+                             tooltip="Port for the overlay WebSocket communication. Used for experimental overlay features.",
+                             row=self.current_row, column=0)
+        self.overlay_websocket_port = ttk.Entry(wip_frame)
+        self.overlay_websocket_port.insert(0, str(self.settings.wip.overlay_websocket_port))
+        self.overlay_websocket_port.grid(row=self.current_row, column=1, sticky='EW', pady=2)
+        self.current_row += 1
+
+        HoverInfoLabelWidget(wip_frame, text="Overlay WebSocket Send:",
+                             tooltip="Enable to send overlay data via WebSocket. Experimental feature.",
+                             row=self.current_row, column=0)
+        self.overlay_websocket_send = tk.BooleanVar(value=self.settings.wip.overlay_websocket_send)
+        ttk.Checkbutton(wip_frame, variable=self.overlay_websocket_send, bootstyle="round-toggle").grid(
+            row=self.current_row, column=1, sticky='W', pady=2)
+        self.current_row += 1
+
+        self.add_reset_button(wip_frame, "wip", self.current_row, 0, self.create_wip_tab)
+
+        for col in range(2):
+            wip_frame.grid_columnconfigure(col, weight=0)
+        for row in range(self.current_row):
+            wip_frame.grid_rowconfigure(row, minsize=30)
+
+        return wip_frame
 
     def on_profile_change(self, event):
         self.save_settings(profile_change=True)

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/GameSentenceMiner/gametext.py

@@ -9,7 +9,7 @@ from websockets import InvalidStatus
 from GameSentenceMiner.util.gsm_utils import do_text_replacements, TEXT_REPLACEMENTS_FILE, run_new_thread
 from GameSentenceMiner.util.configuration import *
 from GameSentenceMiner.util.text_log import *
-from GameSentenceMiner.web.texthooking_page import add_event_to_texthooker
+from GameSentenceMiner.web.texthooking_page import add_event_to_texthooker, send_word_coordinates_to_overlay
 from GameSentenceMiner.wip import get_overlay_coords
 
 current_line = ''
@@ -123,9 +123,13 @@ async def handle_new_text_event(current_clipboard, line_time=None):
     current_line_time = line_time if line_time else datetime.now()
     gsm_status.last_line_received = current_line_time.strftime("%Y-%m-%d %H:%M:%S")
     add_line(current_line_after_regex, line_time)
-    boxes = await find_box_for_sentence(current_line)
     if len(get_text_log().values) > 0:
-        await add_event_to_texthooker(get_text_log()[-1], boxes=boxes)
+        await add_event_to_texthooker(get_text_log()[-1])
+    if get_config().wip.overlay_websocket_port and get_config().wip.overlay_websocket_send:
+        boxes = await find_box_for_sentence(current_line_after_regex)
+        if boxes:
+            await send_word_coordinates_to_overlay(boxes)
+    
 
 async def find_box_for_sentence(sentence):
     boxes = []

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/GameSentenceMiner/owocr/owocr/ocr.py

@@ -6,14 +6,13 @@ from pathlib import Path
 import sys
 import platform
 import logging
-from math import sqrt, floor
+from math import sqrt
 import json
 import base64
 from urllib.parse import urlparse, parse_qs
 
 import jaconv
 import numpy as np
-import rapidfuzz.fuzz
 from PIL import Image
 from loguru import logger
 import requests
@@ -165,28 +164,6 @@ def limit_image_size(img, max_size):
     return False, ''
 
 
-def get_regex(lang):
-    if lang == "ja":
-        return re.compile(r'[\u3041-\u3096\u30A1-\u30FA\u4E00-\u9FFF]')
-    elif lang == "zh":
-        return re.compile(r'[\u4E00-\u9FFF]')
-    elif lang == "ko":
-        return re.compile(r'[\uAC00-\uD7AF]')
-    elif lang == "ar":
-        return re.compile(r'[\u0600-\u06FF\u0750-\u077F\u08A0-\u08FF\uFB50-\uFDFF\uFE70-\uFEFF]')
-    elif lang == "ru":
-        return re.compile(r'[\u0400-\u04FF\u0500-\u052F\u2DE0-\u2DFF\uA640-\uA69F\u1C80-\u1C8F]')
-    elif lang == "el":
-        return re.compile(r'[\u0370-\u03FF\u1F00-\u1FFF]')
-    elif lang == "he":
-        return re.compile(r'[\u0590-\u05FF\uFB1D-\uFB4F]')
-    elif lang == "th":
-        return re.compile(r'[\u0E00-\u0E7F]')
-    else:
-        return re.compile(
-        r'[a-zA-Z\u00C0-\u00FF\u0100-\u017F\u0180-\u024F\u0250-\u02AF\u1D00-\u1D7F\u1D80-\u1DBF\u1E00-\u1EFF\u2C60-\u2C7F\uA720-\uA7FF\uAB30-\uAB6F]')
-
-
 class MangaOcr:
     name = 'mangaocr'
     readable_name = 'Manga OCR'
@@ -266,20 +243,15 @@ class GoogleLens:
     available = False
 
     def __init__(self, lang='ja'):
-        self.regex = get_regex(lang)
-        self.initial_lang = lang
+        self.kana_kanji_regex = re.compile(r'[\u3041-\u3096\u30A1-\u30FA\u4E00-\u9FFF]')
         if 'betterproto' not in sys.modules:
             logger.warning('betterproto not available, Google Lens will not work!')
         else:
             self.available = True
             logger.info('Google Lens ready')
 
-    def __call__(self, img, furigana_filter_sensitivity=0, return_coords=False):
-        lang = get_ocr_language()
+    def __call__(self, img, furigana_filter_sensitivity=0):
         img, is_path = input_to_pil_image(img)
-        if lang != self.initial_lang:
-            self.initial_lang = lang
-            self.regex = get_regex(lang)
         if not img:
             return (False, 'Invalid image provided')
 
@@ -337,14 +309,12 @@ class GoogleLens:
         response_proto = LensOverlayServerResponse().FromString(res.content)
         response_dict = response_proto.to_dict(betterproto.Casing.SNAKE)
 
-        if os.path.exists(r"C:\Users\Beangate\GSM\Electron App\test"):
-            with open(os.path.join(r"C:\Users\Beangate\GSM\Electron App\test", 'glens_response.json'), 'w', encoding='utf-8') as f:
-                json.dump(response_dict, f, indent=4, ensure_ascii=False)
+        # with open(os.path.join(r"C:\Users\Beangate\GSM\Electron App\test", 'glens_response.json'), 'w', encoding='utf-8') as f:
+        #     json.dump(response_dict, f, indent=4, ensure_ascii=False)
         res = ''
         text = response_dict['objects_response']['text']
         skipped = []
         previous_line = None
-        lines = []
         if 'text_layout' in text:
             for paragraph in text['text_layout']['paragraphs']:
                 if previous_line:
@@ -360,38 +330,18 @@ class GoogleLens:
                     if vertical_space > avg_height * 2:
                         res += 'BLANK_LINE'
                 for line in paragraph['lines']:
-                    # Build a list of word boxes for this line
-                    words_info = []
-                    for word in line['words']:
-                        word_info = {
-                            "word": word['plain_text'],
-                            "x1": int(word['geometry']['bounding_box']['center_x'] * img.width - (word['geometry']['bounding_box']['width'] * img.width) / 2),
-                            "y1": int(word['geometry']['bounding_box']['center_y'] * img.height - (word['geometry']['bounding_box']['height'] * img.height) / 2),
-                            "x2": int(word['geometry']['bounding_box']['center_x'] * img.width + (word['geometry']['bounding_box']['width'] * img.width) / 2),
-                            "y2": int(word['geometry']['bounding_box']['center_y'] * img.height + (word['geometry']['bounding_box']['height'] * img.height) / 2)
-                        }
-                        words_info.append(word_info)
-
-                    line_text = ''.join([w['word'] for w in words_info])
-                    line_box = {
-                        "sentence": line_text,
-                        "words": words_info
-                    }
-
-                    # Optionally apply furigana filter
                     if furigana_filter_sensitivity:
-                        line_width = line['geometry']['bounding_box']['width'] * img.width
-                        line_height = line['geometry']['bounding_box']['height'] * img.height
-                        if furigana_filter_sensitivity < line_width and furigana_filter_sensitivity < line_height and self.regex.search(line_text):
-                            for w in words_info:
-                                res += w['word']
+                        if furigana_filter_sensitivity < line['geometry']['bounding_box']['width'] * img.width and furigana_filter_sensitivity < line['geometry']['bounding_box']['height'] * img.height:
+                            for word in line['words']:
+                                res += word['plain_text'] + word['text_separator']
                         else:
-                            skipped.extend([w['word'] for w in words_info])
+                            skipped.append(word['plain_text'] for word in line['words'])
                             continue
                     else:
-                        for w in words_info:
-                            res += w['word']
-                    lines.append(line_box)
+                        for word in line['words']:
+                                res += word['plain_text'] + word['text_separator']
+                        else:
+                            continue
                 previous_line = paragraph
                 res += '\n'
             # logger.info(
@@ -434,11 +384,8 @@ class GoogleLens:
         #                 else:
         #                     continue
         #             res += '\n'
-        
-        if return_coords:
-            x = (True, res, lines)
-        else:
-            x = (True, res)
+
+        x = (True, res)
 
         # img.close()
         return x
@@ -865,7 +812,7 @@ class OneOCR:
 
     def __init__(self, config={}, lang='ja'):
         self.initial_lang = lang
-        self.regex = get_regex(lang)
+        self.get_regex(lang)
         if sys.platform == 'win32':
             if int(platform.release()) < 10:
                 logger.warning('OneOCR is not supported on Windows older than 10!')
@@ -887,11 +834,32 @@ class OneOCR:
             except:
                 logger.warning('Error reading URL from config, OneOCR will not work!')
 
-    def __call__(self, img, furigana_filter_sensitivity=0, sentence_to_check=None):
+    def get_regex(self, lang):
+        if lang == "ja":
+            self.regex = re.compile(r'[\u3041-\u3096\u30A1-\u30FA\u4E00-\u9FFF]')
+        elif lang == "zh":
+            self.regex = re.compile(r'[\u4E00-\u9FFF]')
+        elif lang == "ko":
+            self.regex = re.compile(r'[\uAC00-\uD7AF]')
+        elif lang == "ar":
+            self.regex = re.compile(r'[\u0600-\u06FF\u0750-\u077F\u08A0-\u08FF\uFB50-\uFDFF\uFE70-\uFEFF]')
+        elif lang == "ru":
+            self.regex = re.compile(r'[\u0400-\u04FF\u0500-\u052F\u2DE0-\u2DFF\uA640-\uA69F\u1C80-\u1C8F]')
+        elif lang == "el":
+            self.regex = re.compile(r'[\u0370-\u03FF\u1F00-\u1FFF]')
+        elif lang == "he":
+            self.regex = re.compile(r'[\u0590-\u05FF\uFB1D-\uFB4F]')
+        elif lang == "th":
+            self.regex = re.compile(r'[\u0E00-\u0E7F]')
+        else:
+            self.regex = re.compile(
+            r'[a-zA-Z\u00C0-\u00FF\u0100-\u017F\u0180-\u024F\u0250-\u02AF\u1D00-\u1D7F\u1D80-\u1DBF\u1E00-\u1EFF\u2C60-\u2C7F\uA720-\uA7FF\uAB30-\uAB6F]')
+
+    def __call__(self, img, furigana_filter_sensitivity=0):
         lang = get_ocr_language()
         if lang != self.initial_lang:
             self.initial_lang = lang
-            self.regex = get_regex(lang)
+            self.get_regex(lang)
         img, is_path = input_to_pil_image(img)
         if img.width < 51 or img.height < 51:
             new_width = max(img.width, 51)
@@ -911,6 +879,7 @@ class OneOCR:
                 y_coords = [line['bounding_rect'][f'y{i}'] for line in filtered_lines for i in range(1, 5)]
                 if x_coords and y_coords:
                     crop_coords = (min(x_coords) - 5, min(y_coords) - 5, max(x_coords) + 5, max(y_coords) + 5)
+
                 # with open(os.path.join(get_temporary_directory(), 'oneocr_response.json'), 'w',
                 #           encoding='utf-8') as f:
                 #     json.dump(ocr_resp, f, indent=4, ensure_ascii=False)
@@ -965,37 +934,8 @@ class OneOCR:
                     #         else:
                     #             continue
                     #     res += '\n'
-                elif sentence_to_check:
-                    lines_to_build_area = []
-                    widths = []
-                    heights = []
-                    for line in ocr_resp['lines']:
-                        print(line['text'])
-                        if sentence_to_check in line['text'] or line['text'] in sentence_to_check or rapidfuzz.fuzz.partial_ratio(sentence_to_check, line['text']) > 50:
-                            lines_to_build_area.append(line)
-                            res += line['text']
-                            for word in line['words']:
-                                widths.append(word['bounding_rect']['x2'] - word['bounding_rect']['x1'])
-                                heights.append(word['bounding_rect']['y3'] - word['bounding_rect']['y1'])
-
-                    x_coords = [line['bounding_rect'][f'x{i}'] for line in lines_to_build_area for i in
-                                range(1, 5)]
-                    y_coords = [line['bounding_rect'][f'y{i}'] for line in lines_to_build_area for i in
-                                range(1, 5)]
-                    if widths:
-                        avg_width = sum(widths) / len(widths)
-                    if heights:
-                        avg_height = sum(heights) / len(heights)
-                    if x_coords and y_coords:
-                        crop_coords = (
-                            min(x_coords) - 5, min(y_coords) - 5, max(x_coords) + 5, max(y_coords) + 5)
                 else:
-                    x_coords = [line['bounding_rect'][f'x{i}'] for line in ocr_resp['lines'] for i in range(1, 5)]
-                    y_coords = [line['bounding_rect'][f'y{i}'] for line in ocr_resp['lines'] for i in range(1, 5)]
-                    if x_coords and y_coords:
-                        crop_coords = (min(x_coords) - 5, min(y_coords) - 5, max(x_coords) + 5, max(y_coords) + 5)
                     res = ocr_resp['text']
-
             except RuntimeError as e:
                 return (False, e)
         else:
@@ -1010,9 +950,10 @@ class OneOCR:
                 return (False, 'Unknown error!')
 
             res = res.json()['text']
+
         x = (True, res, crop_coords)
-        if is_path:
-            img.close()
+
+        # img.close()
         return x
 
     def _preprocess(self, img):

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/GameSentenceMiner/owocr/owocr/run.py

@@ -384,6 +384,7 @@ class TextFiltering:
                 block_filtered = self.latin_extended_regex.findall(block)
             else:
                 block_filtered = self.latin_extended_regex.findall(block)
+
             if block_filtered:
                 orig_text_filtered.append(''.join(block_filtered))
             else:
@@ -547,39 +548,6 @@ class ScreenshotThread(threading.Thread):
             else:
                 raise ValueError('Window capture is only currently supported on Windows and macOS')
 
-    def __del__(self):
-        if self.macos_window_tracker_instance:
-            self.macos_window_tracker_instance.join()
-        elif self.windows_window_tracker_instance:
-            self.windows_window_tracker_instance.join()
-
-    def setup_persistent_windows_window_tracker(self):
-        global window_open
-        window_open = False
-        def setup_tracker():
-            global window_open
-            self.window_handle, window_title = self.get_windows_window_handle(self.screen_capture_window)
-
-            if not self.window_handle:
-                # print(f"Window '{screen_capture_window}' not found.")
-                return
-
-            set_dpi_awareness()
-            window_open = True
-            self.windows_window_tracker_instance = threading.Thread(target=self.windows_window_tracker)
-            self.windows_window_tracker_instance.start()
-            logger.opt(ansi=True).info(f'Selected window: {window_title}')
-
-        while not terminated:
-            if not window_open:
-                try:
-                    setup_tracker()
-                except ValueError as e:
-                    logger.error(f"Error setting up persistent windows window tracker: {e}")
-                    break
-            time.sleep(5)
-
-
     def get_windows_window_handle(self, window_title):
         def callback(hwnd, window_title_part):
             window_title = win32gui.GetWindowText(hwnd)
@@ -602,7 +570,7 @@ class ScreenshotThread(threading.Thread):
 
     def windows_window_tracker(self):
         found = True
-        while not terminated or window_open:
+        while not terminated:
             found = win32gui.IsWindow(self.window_handle)
             if not found:
                 break
@@ -1118,11 +1086,10 @@ def signal_handler(sig, frame):
 
 
 def on_window_closed(alive):
-    global terminated, window_open
+    global terminated
     if not (alive or terminated):
         logger.info('Window closed or error occurred, terminated!')
-        window_open = False
-        # terminated = True
+        terminated = True
 
 
 def on_screenshot_combo():

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/GameSentenceMiner/util/configuration.py

@@ -15,6 +15,7 @@ from enum import Enum
 import toml
 from dataclasses_json import dataclass_json
 
+
 OFF = 'OFF'
 # VOSK = 'VOSK'
 SILERO = 'SILERO'
@@ -71,10 +72,232 @@ class Language(Enum):
     PORTUGUESE = "pt"
     HINDI = "hi"
     ARABIC = "ar"
+    TURKISH = "tr"
+    DUTCH = "nl"
+    SWEDISH = "sv"
+    FINNISH = "fi"
+    DANISH = "da"
+    NORWEGIAN = "no"
+    
 
 AVAILABLE_LANGUAGES = [lang.value for lang in Language]
 AVAILABLE_LANGUAGES_DICT = {lang.value: lang for lang in Language}
 
+class CommonLanguages(str, Enum):
+    """
+    An Enum of the world's most common languages, based on total speaker count.
+
+    The enum member is the common English name (e.g., ENGLISH) and its
+    value is the ISO 639-1 two-letter code (e.g., 'en').
+
+    Inheriting from `str` allows for direct comparison and use in functions
+    that expect a string, e.g., `CommonLanguages.FRENCH == 'fr'`.
+
+    This list is curated from Wikipedia's "List of languages by total number of speakers"
+    and contains over 200 entries to provide broad but practical coverage.
+    """
+    ENGLISH = 'en'
+    AFRIKAANS = 'af'
+    AKAN = 'ak'
+    ALBANIAN = 'sq'
+    ALGERIAN_SPOKEN_ARABIC = 'arq'
+    AMHARIC = 'am'
+    ARMENIAN = 'hy'
+    ASSAMESE = 'as'
+    BAMBARA = 'bm'
+    BASQUE = 'eu'
+    BELARUSIAN = 'be'
+    BENGALI = 'bn'
+    BHOJPURI = 'bho'
+    BOSNIAN = 'bs'
+    BODO = 'brx'
+    BULGARIAN = 'bg'
+    BURMESE = 'my'
+    CAPE_VERDEAN_CREOLE = 'kea'
+    CATALAN = 'ca'
+    CEBUANO = 'ceb'
+    CHHATTISGARHI = 'hns'
+    CHITTAGONIAN = 'ctg'
+    CROATIAN = 'hr'
+    CZECH = 'cs'
+    DANISH = 'da'
+    DECCAN = 'dcc'
+    DOGRI = 'doi'
+    DZONGKHA = 'dz'
+    DUTCH = 'nl'
+    EGYPTIAN_SPOKEN_ARABIC = 'arz'
+    ESTONIAN = 'et'
+    EWE = 'ee'
+    FAROESE = 'fo'
+    FIJIAN = 'fj'
+    FINNISH = 'fi'
+    FRENCH = 'fr'
+    GALICIAN = 'gl'
+    GAN_CHINESE = 'gan'
+    GEORGIAN = 'ka'
+    GERMAN = 'de'
+    GREEK = 'el'
+    GREENLANDIC = 'kl'
+    GUJARATI = 'gu'
+    HAITIAN_CREOLE = 'ht'
+    HAUSA = 'ha'
+    HAKKA_CHINESE = 'hak'
+    HARYANVI = 'bgc'
+    HEBREW = 'he'
+    HINDI = 'hi'
+    HUNGARIAN = 'hu'
+    ICELANDIC = 'is'
+    IGBO = 'ig'
+    INDONESIAN = 'id'
+    IRANIAN_PERSIAN = 'fa'
+    IRISH = 'ga'
+    ITALIAN = 'it'
+    JAVANESE = 'jv'
+    JAMAICAN_PATOIS = 'jam'
+    JAPANESE = 'ja'
+    KANNADA = 'kn'
+    KASHMIRI = 'ks'
+    KAZAKH = 'kk'
+    KHMER = 'km'
+    KONGO = 'kg'
+    KONKANI = 'kok'
+    KOREAN = 'ko'
+    KURDISH = 'kmr'
+    LAO = 'lo'
+    LATVIAN = 'lv'
+    LINGALA = 'ln'
+    LITHUANIAN = 'lt'
+    LUBA_KASAI = 'lua'
+    LUXEMBOURGISH = 'lb'
+    MACEDONIAN = 'mk'
+    MADURESE = 'mad'
+    MAGAHI = 'mag'
+    MAITHILI = 'mai'
+    MALAGASY = 'mg'
+    MALAYALAM = 'ml'
+    MALTESE = 'mt'
+    MANDARIN_CHINESE = 'zh'
+    MANIPURI = 'mni'
+    MARATHI = 'mr'
+    MAORI = 'mi'
+    MAURITIAN_CREOLE = 'mfe'
+    MIN_NAN_CHINESE = 'nan'
+    MINANGKABAU = 'min'
+    MONGOLIAN = 'mn'
+    MONTENEGRIN = 'cnr'
+    MOROCCAN_SPOKEN_ARABIC = 'ary'
+    NDEBELE = 'nr'
+    NEPALI = 'ne'
+    NIGERIAN_PIDGIN = 'pcm'
+    NORTHERN_KURDISH = 'kmr'
+    NORTHERN_PASHTO = 'pbu'
+    NORTHERN_UZBEK = 'uz'
+    NORWEGIAN = 'no'
+    ODIA = 'or'
+    PAPIAMENTO = 'pap'
+    POLISH = 'pl'
+    PORTUGUESE = 'pt'
+    ROMANIAN = 'ro'
+    RWANDA = 'rw'
+    RUSSIAN = 'ru'
+    SAMOAN = 'sm'
+    SANTALI = 'sat'
+    SARAIKI = 'skr'
+    SCOTTISH_GAELIC = 'gd'
+    SEYCHELLOIS_CREOLE = 'crs'
+    SERBIAN = 'sr'
+    SHONA = 'sn'
+    SINDHI = 'sd'
+    SINHALA = 'si'
+    SLOVAK = 'sk'
+    SLOVENIAN = 'sl'
+    SOMALI = 'so'
+    SOTHO = 'st'
+    SOUTH_AZERBAIJANI = 'azb'
+    SOUTHERN_PASHTO = 'ps'
+    SPANISH = 'es'
+    STANDARD_ARABIC = 'ar'
+    SUDANESE_SPOKEN_ARABIC = 'apd'
+    SUNDANESE = 'su'
+    SWAHILI = 'sw'
+    SWATI = 'ss'
+    SWEDISH = 'sv'
+    SYLHETI = 'syl'
+    TAGALOG = 'tl'
+    TAMIL = 'ta'
+    TELUGU = 'te'
+    THAI = 'th'
+    TIGRINYA = 'ti'
+    TIBETAN = 'bo'
+    TONGAN = 'to'
+    TSONGA = 'ts'
+    TSWANA = 'tn'
+    TWI = 'twi'
+    UKRAINIAN = 'uk'
+    URDU = 'ur'
+    UYGHUR = 'ug'
+    VENDA = 've'
+    VIETNAMESE = 'vi'
+    WELSH = 'cy'
+    WESTERN_PUNJABI = 'pnb'
+    WOLOF = 'wo'
+    WU_CHINESE = 'wuu'
+    XHOSA = 'xh'
+    YORUBA = 'yo'
+    YUE_CHINESE = 'yue'
+    ZULU = 'zu'
+    
+
+    # Helper methods
+    @classmethod
+    def get_all_codes(cls) -> list[str]:
+        """Returns a list of all language codes (e.g., ['en', 'zh', 'hi'])."""
+        return [lang.value for lang in cls]
+
+    @classmethod
+    def get_all_names(cls) -> list[str]:
+        """Returns a list of all language names (e.g., ['ENGLISH', 'MANDARIN_CHINESE'])."""
+        return [lang.name for lang in cls]
+    
+    @classmethod
+    def get_all_names_pretty(cls) -> list[str]:
+        """Returns a list of all language names formatted for display (e.g., ['English', 'Mandarin Chinese'])."""
+        return [lang.name.replace('_', ' ').title() for lang in cls]
+
+    @classmethod
+    def get_choices(cls) -> list[tuple[str, str]]:
+        """
+        Returns a list of (value, label) tuples for use in web framework
+        choice fields (e.g., Django, Flask).
+
+        Example: [('en', 'English'), ('zh', 'Mandarin Chinese')]
+        """
+        return [(lang.value, lang.name.replace('_', ' ').title()) for lang in cls]
+    
+    # Method to lookup language by it's name
+    @classmethod
+    def from_name(cls, name: str) -> 'CommonLanguages':
+        """
+        Looks up a language by its name (e.g., 'ENGLISH') and returns the corresponding enum member.
+        Raises ValueError if not found.
+        """
+        try:
+            return cls[name]
+        except KeyError:
+            raise ValueError(f"Language '{name}' not found in CommonLanguages")
+        
+    # Method to lookup language by its code
+    @classmethod
+    def from_code(cls, code: str) -> 'CommonLanguages':
+        """
+        Looks up a language by its code (e.g., 'en') and returns the corresponding enum member.
+        Raises ValueError if not found.
+        """
+        for lang in cls:
+            if lang.value == code:
+                return lang
+        raise ValueError(f"Language code '{code}' not found in CommonLanguages")
+
 @dataclass_json
 @dataclass
 class General:
@@ -86,6 +309,7 @@ class General:
     open_multimine_on_startup: bool = True
     texthook_replacement_regex: str = ""
     texthooker_port: int = 55000
+    native_language: str = CommonLanguages.ENGLISH.value
 
 
 @dataclass_json
@@ -283,6 +507,16 @@ class Ai:
                 self.provider = AI_GEMINI
             if self.provider == 'groq':
                 self.provider = AI_GROQ
+                
+                
+# Experimental Features section, will change often
+@dataclass_json
+@dataclass
+class WIP:
+    overlay_websocket_port: int = 55003
+    overlay_websocket_send: bool = False
+                    
+
 
 @dataclass_json
 @dataclass
@@ -300,6 +534,7 @@ class ProfileConfig:
     vad: VAD = field(default_factory=VAD)
     advanced: Advanced = field(default_factory=Advanced)
     ai: Ai = field(default_factory=Ai)
+    wip: WIP = field(default_factory=WIP)
 
 
     # This is just for legacy support
@@ -481,6 +716,7 @@ class Config:
             self.sync_shared_field(config, profile, "advanced")
             self.sync_shared_field(config, profile, "paths")
             self.sync_shared_field(config, profile, "obs")
+            self.sync_shared_field(config, profile, "wip")
             self.sync_shared_field(config.ai, profile.ai, "anki_field")
             self.sync_shared_field(config.ai, profile.ai, "provider")
             self.sync_shared_field(config.ai, profile.ai, "api_key")

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/GameSentenceMiner/util/model.py

@@ -1,5 +1,6 @@
 from dataclasses import dataclass
 from typing import Optional, List
+from enum import Enum
 
 from dataclasses_json import dataclass_json
 

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/GameSentenceMiner/web/texthooking_page.py

@@ -259,7 +259,7 @@ def clear_history():
     return jsonify({'message': 'History cleared successfully'}), 200
 
 
-async def add_event_to_texthooker(line: GameLine, boxes=None):
+async def add_event_to_texthooker(line: GameLine):
     new_event = event_manager.add_gameline(line)
     await websocket_server_thread.send_text({
         'event': 'text_received',
@@ -268,6 +268,9 @@ async def add_event_to_texthooker(line: GameLine, boxes=None):
     })
     if get_config().advanced.plaintext_websocket_port:
         await plaintext_websocket_server_thread.send_text(line.text)
+        
+        
+async def send_word_coordinates_to_overlay(boxes):
     if boxes and len(boxes) > 0 and overlay_server_thread:
         await overlay_server_thread.send_text(boxes)
 

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/GameSentenceMiner.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: GameSentenceMiner
-Version: 2.12.0.dev2
+Version: 2.12.0.dev3
 Summary: A tool for mining sentences from games. Update: Overlay?
 Author-email: Beangate <bpwhelan95@gmail.com>
 License: MIT License

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: GameSentenceMiner
-Version: 2.12.0.dev2
+Version: 2.12.0.dev3
 Summary: A tool for mining sentences from games. Update: Overlay?
 Author-email: Beangate <bpwhelan95@gmail.com>
 License: MIT License

{gamesentenceminer-2.12.0.dev2 → gamesentenceminer-2.12.0.dev3}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "GameSentenceMiner"
-version = "2.12.0-dev2"
+version = "2.12.0-dev3"
 description = "A tool for mining sentences from games. Update: Overlay?"
 readme = "README.md"
 requires-python = ">=3.10"