GameSentenceMiner 2.8.13__py3-none-any.whl → 2.8.15__py3-none-any.whl

GameSentenceMiner/anki.py

@@ -282,7 +282,7 @@ def update_new_card():
         texthooking_page.reset_checked_lines()
     else:
         logger.info("New card(s) detected! Added to Processing Queue!")
-        card_queue.append(last_card)
+        card_queue.append((last_card, datetime.now()))
         try:
             obs.save_replay_buffer()
         except Exception as e:

GameSentenceMiner/config_gui.py

@@ -157,8 +157,9 @@ class ConfigApp:
                 custom_ffmpeg_settings=self.screenshot_custom_ffmpeg_settings.get(),
                 screenshot_hotkey_updates_anki=self.screenshot_hotkey_update_anki.get(),
                 seconds_after_line = self.seconds_after_line.get(),
-                use_beginning_of_line_as_screenshot=self.use_beginning_of_line_as_screenshot.get(),
-                use_new_screenshot_logic=self.use_new_screenshot_logic.get()
+                # use_beginning_of_line_as_screenshot=self.use_beginning_of_line_as_screenshot.get(),
+                # use_new_screenshot_logic=self.use_new_screenshot_logic.get(),
+                screenshot_timing_setting=self.screenshot_timing.get()
             ),
             audio=Audio(
                 enabled=self.audio_enabled.get(),
@@ -199,10 +200,11 @@ class ConfigApp:
             advanced=Advanced(
                 audio_player_path=self.audio_player_path.get(),
                 video_player_path=self.video_player_path.get(),
-                show_screenshot_buttons=self.show_screenshot_button.get(),
+                # show_screenshot_buttons=self.show_screenshot_button.get(),
                 multi_line_line_break=self.multi_line_line_break.get(),
                 multi_line_sentence_storage_field=self.multi_line_sentence_storage_field.get(),
                 ocr_sends_to_clipboard=self.ocr_sends_to_clipboard.get(),
+                use_anki_note_creation_time=self.use_anki_note_creation_time.get(),
             ),
             ai=Ai(
                 enabled=self.ai_enabled.get(),
@@ -754,28 +756,46 @@ class ConfigApp:
         self.add_label_and_increment_row(screenshot_frame, "Custom FFmpeg options for re-encoding screenshots.",
                                          row=self.current_row, column=2)
 
+
         ttk.Label(screenshot_frame, text="Screenshot Hotkey Updates Anki:").grid(row=self.current_row, column=0, sticky='W')
         self.screenshot_hotkey_update_anki = tk.BooleanVar(value=self.settings.screenshot.screenshot_hotkey_updates_anki)
         ttk.Checkbutton(screenshot_frame, variable=self.screenshot_hotkey_update_anki).grid(row=self.current_row, column=1, sticky='W')
         self.add_label_and_increment_row(screenshot_frame, "Enable to allow Screenshot hotkey/button to update the latest anki card.", row=self.current_row,
                                          column=2)
 
-        ttk.Label(screenshot_frame, text="Seconds After Line to SS:").grid(row=self.current_row, column=0, sticky='W')
+        ttk.Label(screenshot_frame, text="Screenshot Timing:").grid(row=self.current_row, column=0, sticky='W')
+        self.screenshot_timing = ttk.Combobox(screenshot_frame, values=['beginning', 'middle', 'end'])
+        self.screenshot_timing.insert(0, self.settings.screenshot.screenshot_timing_setting)
+        self.screenshot_timing.grid(row=self.current_row, column=1)
+        self.add_label_and_increment_row(screenshot_frame, "Select when to take the screenshot relative to the line: beginning, middle, or end.", row=self.current_row,
+                                            column=2)
+
+        ttk.Label(screenshot_frame, text="Screenshot Offset:").grid(row=self.current_row, column=0, sticky='W')
         self.seconds_after_line = ttk.Entry(screenshot_frame)
         self.seconds_after_line.insert(0, str(self.settings.screenshot.seconds_after_line))
         self.seconds_after_line.grid(row=self.current_row, column=1)
-        self.add_label_and_increment_row(screenshot_frame, "This is only used for mining from lines from history (not current line)", row=self.current_row,
+        self.add_label_and_increment_row(screenshot_frame, "Time in seconds to offset the screenshot based on the Timing setting above (should almost always be positive)", row=self.current_row,
                                          column=2)
 
-        ttk.Label(screenshot_frame, text="Use Beginning of Line as Screenshot:").grid(row=self.current_row, column=0, sticky='W')
-        self.use_beginning_of_line_as_screenshot = tk.BooleanVar(value=self.settings.screenshot.use_beginning_of_line_as_screenshot)
-        ttk.Checkbutton(screenshot_frame, variable=self.use_beginning_of_line_as_screenshot).grid(row=self.current_row, column=1, sticky='W')
-        self.add_label_and_increment_row(screenshot_frame, "Enable to use the beginning of the line as the screenshot point. Adjust the above setting to fine-tine timing.", row=self.current_row, column=2)
-
-        ttk.Label(screenshot_frame, text="Use alternative screenshot logic:").grid(row=self.current_row, column=0, sticky='W')
-        self.use_new_screenshot_logic = tk.BooleanVar(value=self.settings.screenshot.use_new_screenshot_logic)
-        ttk.Checkbutton(screenshot_frame, variable=self.use_new_screenshot_logic).grid(row=self.current_row, column=1, sticky='W')
-        self.add_label_and_increment_row(screenshot_frame, "Enable to use the new screenshot logic. This will try to take the screenshot in the middle of the voiceline, or middle of the line if no audio/vad.", row=self.current_row, column=2)
+        # ttk.Label(screenshot_frame, text="Use Beginning of Line as Screenshot:").grid(row=self.current_row, column=0, sticky='W')
+        # self.use_beginning_of_line_as_screenshot = tk.BooleanVar(value=self.settings.screenshot.use_beginning_of_line_as_screenshot)
+        # ttk.Checkbutton(screenshot_frame, variable=self.use_beginning_of_line_as_screenshot).grid(row=self.current_row, column=1, sticky='W')
+        # self.add_label_and_increment_row(screenshot_frame, "Enable to use the beginning of the line as the screenshot point. Adjust the above setting to fine-tine timing.", row=self.current_row, column=2)
+        #
+        # ttk.Label(screenshot_frame, text="Use alternative screenshot logic:").grid(row=self.current_row, column=0, sticky='W')
+        # self.use_new_screenshot_logic = tk.BooleanVar(value=self.settings.screenshot.use_new_screenshot_logic)
+        # ttk.Checkbutton(screenshot_frame, variable=self.use_new_screenshot_logic).grid(row=self.current_row, column=1, sticky='W')
+        # self.add_label_and_increment_row(screenshot_frame, "Enable to use the new screenshot logic. This will try to take the screenshot in the middle of the voiceline, or middle of the line if no audio/vad.", row=self.current_row, column=2)
+        #
+
+    def update_audio_ffmpeg_settings(self, event):
+        selected_option = self.ffmpeg_preset_options.get()
+        if selected_option in self.ffmpeg_preset_options_map:
+            self.ffmpeg_reencode_options.delete(0, tk.END)
+            self.ffmpeg_reencode_options.insert(0, self.ffmpeg_preset_options_map[selected_option])
+        else:
+            self.ffmpeg_reencode_options.delete(0, tk.END)
+            self.ffmpeg_reencode_options.insert(0, "")
 
     @new_tab
     def create_audio_tab(self):
@@ -807,6 +827,28 @@ class ConfigApp:
         self.add_label_and_increment_row(audio_frame, "Offset in seconds to end audio processing.",
                                          row=self.current_row, column=2)
 
+        ttk.Label(audio_frame, text="FFmpeg Preset Options:").grid(row=self.current_row, column=0, sticky='W')
+
+        # Define display names and their corresponding values
+        self.ffmpeg_preset_options_map = {
+            "No Re-encode" : "",
+            "Simple loudness normalization (Simplest, Start Here)": "-c:a libopus -f opus -af \"loudnorm=I=-23:LRA=7:TP=-2\"",
+            "Downmix to mono with normalization (Recommended(?))": "-c:a libopus -ac 1 -f opus -application voip -apply_phase_inv 0 -af \"loudnorm=I=-23:dual_mono=true\"",
+            "Downmix to mono, 30kbps, normalized (Optimal(?))": "-c:a libopus -b:a 30k -ac 1 -f opus -application voip -apply_phase_inv 0 -af \"loudnorm=I=-23:dual_mono=true\"",
+
+        }
+
+        # Create a Combobox with display names
+        self.ffmpeg_preset_options = ttk.Combobox(audio_frame, values=list(self.ffmpeg_preset_options_map.keys()), width=50)
+        # self.ffmpeg_preset_options.set("Downmix to mono with normalization")  # Set default display name
+        self.ffmpeg_preset_options.grid(row=self.current_row, column=1)
+
+        # Bind selection to update settings
+        self.ffmpeg_preset_options.bind("<<ComboboxSelected>>", self.update_audio_ffmpeg_settings)
+
+        self.add_label_and_increment_row(audio_frame, "Select a preset FFmpeg option for re-encoding screenshots.",
+                                         row=self.current_row, column=2)
+
         ttk.Label(audio_frame, text="FFmpeg Reencode Options:").grid(row=self.current_row, column=0, sticky='W')
         self.ffmpeg_reencode_options = ttk.Entry(audio_frame, width=50)
         self.ffmpeg_reencode_options.insert(0, self.settings.audio.ffmpeg_reencode_options)
@@ -814,6 +856,7 @@ class ConfigApp:
         self.add_label_and_increment_row(audio_frame, "Custom FFmpeg options for re-encoding audio files.",
                                          row=self.current_row, column=2)
 
+
         ttk.Label(audio_frame, text="Anki Media Collection:").grid(row=self.current_row, column=0, sticky='W')
         self.anki_media_collection = ttk.Entry(audio_frame)
         self.anki_media_collection.insert(0, self.settings.audio.anki_media_collection)
@@ -974,11 +1017,6 @@ class ConfigApp:
         self.play_latest_audio_hotkey.grid(row=self.current_row, column=1)
         self.add_label_and_increment_row(advanced_frame, "Hotkey to trim and play the latest audio.", row=self.current_row, column=2)
 
-        ttk.Label(advanced_frame, text="Show Screenshot Button:").grid(row=self.current_row, column=0, sticky='W')
-        self.show_screenshot_button = tk.BooleanVar(value=self.settings.advanced.show_screenshot_buttons)
-        ttk.Checkbutton(advanced_frame, variable=self.show_screenshot_button).grid(row=self.current_row, column=1, sticky='W')
-        self.add_label_and_increment_row(advanced_frame, "Show the screenshot button in the utility gui.", row=self.current_row, column=2)
-
         ttk.Label(advanced_frame, text="Multi-line Line-Break:").grid(row=self.current_row, column=0, sticky='W')
         self.multi_line_line_break = ttk.Entry(advanced_frame)
         self.multi_line_line_break.insert(0, self.settings.advanced.multi_line_line_break)
@@ -997,6 +1035,12 @@ class ConfigApp:
         self.add_label_and_increment_row(advanced_frame, "Enable to send OCR results to clipboard.", row=self.current_row, column=2)
 
 
+        ttk.Label(advanced_frame, text="Use Anki Creation Date for Audio Timing:").grid(row=self.current_row, column=0, sticky='W')
+        self.use_anki_note_creation_time = tk.BooleanVar(value=self.settings.advanced.use_anki_note_creation_time)
+        ttk.Checkbutton(advanced_frame, variable=self.use_anki_note_creation_time).grid(row=self.current_row, column=1, sticky='W')
+        self.add_label_and_increment_row(advanced_frame, "Use the Anki note creation date for audio timing instead of the OBS replay time.", row=self.current_row, column=2)
+
+
 
     @new_tab
     def create_ai_tab(self):

GameSentenceMiner/configuration.py

@@ -109,10 +109,21 @@ class Screenshot:
     quality: str = 85
     extension: str = "webp"
     custom_ffmpeg_settings: str = ''
+    custom_ffmpeg_option_selected: str = ''
     screenshot_hotkey_updates_anki: bool = False
     seconds_after_line: float = 1.0
     use_beginning_of_line_as_screenshot: bool = True
     use_new_screenshot_logic: bool = False
+    screenshot_timing_setting: str = ''  # 'middle', 'end'
+
+    def __post_init__(self):
+        if not self.screenshot_timing_setting and self.use_beginning_of_line_as_screenshot:
+            self.screenshot_timing_setting = 'beginning'
+        if not self.screenshot_timing_setting and self.use_new_screenshot_logic:
+            self.screenshot_timing_setting = 'middle'
+        if not self.screenshot_timing_setting and not self.use_beginning_of_line_as_screenshot and not self.use_new_screenshot_logic:
+            self.screenshot_timing_setting = 'end'
+
 
 
 @dataclass_json
@@ -181,6 +192,7 @@ class Advanced:
     multi_line_line_break: str = '<br>'
     multi_line_sentence_storage_field: str = ''
     ocr_sends_to_clipboard: bool = True
+    use_anki_note_creation_time: bool = False
 
 @dataclass_json
 @dataclass

GameSentenceMiner/ffmpeg.py

@@ -57,6 +57,8 @@ def get_screenshot_time(video_path, game_line, default_beginning=False, vad_begi
         # Assuming initial_time is defined elsewhere if game_line is None
         line_time = initial_time
 
+    logger.info("Calculating screenshot time for line: " + str(game_line.text))
+
     file_length = get_video_duration(video_path)
     file_mod_time = get_file_modification_time(video_path)
 
@@ -69,14 +71,27 @@ def get_screenshot_time(video_path, game_line, default_beginning=False, vad_begi
     if vad_beginning and vad_end and not doing_multi_line:
         logger.debug("Using VAD to determine screenshot time")
         screenshot_time_from_beginning = line_timestamp_in_video + vad_end - screenshot_offset
-    elif get_config().screenshot.use_new_screenshot_logic:
+    elif get_config().screenshot.screenshot_timing_setting == "beginning":
+        logger.debug("Using beginning of line for screenshot")
+        screenshot_time_from_beginning = line_timestamp_in_video + screenshot_offset
+    elif get_config().screenshot.screenshot_timing_setting == "middle":
         if game_line.next:
             logger.debug("Finding time between lines for screenshot")
             screenshot_time_from_beginning = line_timestamp_in_video + ((game_line.next.time - game_line.time).total_seconds() / 2)
         else:
             logger.debug("Using end of line for screenshot")
             screenshot_time_from_beginning = file_length - screenshot_offset
+    elif get_config().screenshot.screenshot_timing_setting == "end":
+        logger.debug("Using end of line for screenshot")
+        if game_line.next:
+            logger.debug("Finding time between lines for screenshot")
+            screenshot_time_from_beginning = line_timestamp_in_video + (game_line.next.time - game_line.time).total_seconds() - screenshot_offset
+        else:
+            logger.debug("Using end of video for screenshot")
+            # If no next line, use the end of the video
+            screenshot_time_from_beginning = file_length - screenshot_offset
     else:
+        logger.error(f"Invalid screenshot timing setting: {get_config().screenshot.screenshot_timing_setting}")
         screenshot_time_from_beginning = line_timestamp_in_video + screenshot_offset
 
     # Check if the calculated time is out of bounds
@@ -150,7 +165,7 @@ def get_audio_codec(video_path):
         return None
 
 
-def get_audio_and_trim(video_path, game_line, next_line_time):
+def get_audio_and_trim(video_path, game_line, next_line_time, anki_card_creation_time):
     supported_formats = {
         'opus': 'libopus',
         'mp3': 'libmp3lame',
@@ -184,7 +199,7 @@ def get_audio_and_trim(video_path, game_line, next_line_time):
 
     subprocess.run(command)
 
-    return trim_audio_based_on_last_line(untrimmed_audio, video_path, game_line, next_line_time)
+    return trim_audio_based_on_last_line(untrimmed_audio, video_path, game_line, next_line_time, anki_card_creation_time)
 
 
 def get_video_duration(file_path):
@@ -202,10 +217,10 @@ def get_video_duration(file_path):
     return float(duration_info["format"]["duration"])  # Return the duration in seconds
 
 
-def trim_audio_based_on_last_line(untrimmed_audio, video_path, game_line, next_line):
+def trim_audio_based_on_last_line(untrimmed_audio, video_path, game_line, next_line, anki_card_creation_time):
     trimmed_audio = tempfile.NamedTemporaryFile(dir=configuration.get_temporary_directory(),
                                                 suffix=f".{get_config().audio.extension}").name
-    start_trim_time, total_seconds, total_seconds_after_offset = get_video_timings(video_path, game_line)
+    start_trim_time, total_seconds, total_seconds_after_offset = get_video_timings(video_path, game_line, anki_card_creation_time)
 
     ffmpeg_command = ffmpeg_base_command_list + [
         "-i", untrimmed_audio,
@@ -232,8 +247,11 @@ def trim_audio_based_on_last_line(untrimmed_audio, video_path, game_line, next_l
     logger.info(f"Audio trimmed and saved to {trimmed_audio}")
     return trimmed_audio
 
-def get_video_timings(video_path, game_line):
-    file_mod_time = get_file_modification_time(video_path)
+def get_video_timings(video_path, game_line, anki_card_creation_time):
+    if anki_card_creation_time and get_config().advanced.use_anki_note_creation_time:
+        file_mod_time = anki_card_creation_time
+    else:
+        file_mod_time = get_file_modification_time(video_path)
     file_length = get_video_duration(video_path)
     time_delta = file_mod_time - game_line.time
     # Convert time_delta to FFmpeg-friendly format (HH:MM:SS.milliseconds)

GameSentenceMiner/gametext.py

@@ -78,13 +78,15 @@ async def listen_websocket():
                 if e.response.status_code == 404:
                     logger.info("Texthooker WebSocket connection failed. Attempting some fixes...")
                     try_other = True
-            if not (isinstance(e, ConnectionResetError) or isinstance(e, ConnectionError) or isinstance(e, InvalidStatus) or isinstance(e, websockets.ConnectionClosed)):
-                logger.error(f"Unexpected error in Texthooker WebSocket connection: {e}")
-            websocket_connected = False
-            if not reconnecting:
-                logger.warning(f"Texthooker WebSocket connection lost, Defaulting to clipboard if enabled. Attempting to Reconnect...")
-            reconnecting = True
-            await asyncio.sleep(5)
+                    await asyncio.sleep(0.1)
+            else:
+                if not (isinstance(e, ConnectionResetError) or isinstance(e, ConnectionError) or isinstance(e, InvalidStatus) or isinstance(e, websockets.ConnectionClosed)):
+                    logger.error(f"Unexpected error in Texthooker WebSocket connection: {e}")
+                websocket_connected = False
+                if not reconnecting:
+                    logger.warning(f"Texthooker WebSocket connection lost, Defaulting to clipboard if enabled. Attempting to Reconnect...")
+                reconnecting = True
+                await asyncio.sleep(5)
 
 async def handle_new_text_event(current_clipboard, line_time=None):
     global current_line, current_line_time, current_line_after_regex

GameSentenceMiner/gsm.py

@@ -90,8 +90,9 @@ class VideoToAudioHandler(FileSystemEventHandler):
             return
         try:
             last_note = None
+            anki_card_creation_time = None
             if anki.card_queue and len(anki.card_queue) > 0:
-                last_note = anki.card_queue.pop(0)
+                last_note, anki_card_creation_time = anki.card_queue.pop(0)
             with util.lock:
                 util.set_last_mined_line(anki.get_sentence(last_note))
                 if os.path.exists(video_path) and os.access(video_path, os.R_OK):
@@ -136,7 +137,8 @@ class VideoToAudioHandler(FileSystemEventHandler):
                     final_audio_output, should_update_audio, vad_trimmed_audio, vad_beginning, vad_end = VideoToAudioHandler.get_audio(
                         start_line,
                         line_cutoff,
-                        video_path)
+                        video_path,
+                        anki_card_creation_time)
                 else:
                     final_audio_output = ""
                     should_update_audio = False
@@ -148,7 +150,7 @@ class VideoToAudioHandler(FileSystemEventHandler):
                     elif not get_config().anki.sentence_audio_field:
                         logger.info("No SentenceAudio Field in config, skipping audio processing!")
 
-                ss_timing = ffmpeg.get_screenshot_time(video_path, mined_line, vad_beginning, vad_end, bool(selected_lines))
+                ss_timing = ffmpeg.get_screenshot_time(video_path, mined_line, vad_beginning=vad_beginning, vad_end=vad_end, doing_multi_line=bool(selected_lines))
 
                 if get_config().anki.update_anki and last_note:
                     anki.update_anki_card(last_note, note, audio_path=final_audio_output, video_path=video_path,
@@ -171,8 +173,8 @@ class VideoToAudioHandler(FileSystemEventHandler):
 
 
     @staticmethod
-    def get_audio(game_line, next_line_time, video_path, temporary=False):
-        trimmed_audio = get_audio_and_trim(video_path, game_line, next_line_time)
+    def get_audio(game_line, next_line_time, video_path, anki_card_creation_time,temporary=False):
+        trimmed_audio = get_audio_and_trim(video_path, game_line, next_line_time, anki_card_creation_time)
         if temporary:
             return trimmed_audio
         vad_trimmed_audio = make_unique_file_name(
@@ -292,8 +294,6 @@ def get_screenshot():
         encoded_image = ffmpeg.process_image(image)
         if get_config().anki.update_anki and get_config().screenshot.screenshot_hotkey_updates_anki:
             last_note = anki.get_last_anki_card()
-            if last_note:
-                logger.debug(json.dumps(last_note))
             if get_config().features.backfill_audio:
                 last_note = anki.get_cards_by_sentence(gametext.current_line)
             if last_note:
@@ -306,7 +306,7 @@ def get_screenshot():
         else:
             notification.send_screenshot_saved(encoded_image)
     except Exception as e:
-        logger.error(f"Failed to get Screenshot {e}")
+        logger.error(f"Failed to get Screenshot: {e}")
 
 
 def create_image():

GameSentenceMiner/ocr/gsm_ocr_config.py

@@ -43,6 +43,7 @@ class OCRConfig:
     coordinate_system: str = None
     window_geometry: Optional[WindowGeometry] = None
     window: Optional[str] = None
+    language: str = "ja"
 
     def __post_init__(self):
         if self.coordinate_system and self.coordinate_system == "percentage" and self.window:

GameSentenceMiner/ocr/owocr_helper.py

@@ -320,7 +320,7 @@ def run_oneocr(ocr_config: OCRConfig, i, area=False):
             text_callback=text_callback,
             screen_capture_exclusions=exclusions,
             rectangle=i,
-            language="ja")
+            language=language)
     done = True
 
 
@@ -335,27 +335,31 @@ def get_window(window_name):
         else:
             return None
     except Exception as e:
-        print(f"Error finding window '{self.window_name}': {e}")
+        print(f"Error finding window '{window_name}': {e}")
         return None
 
 if __name__ == "__main__":
-    global ocr1, ocr2, twopassocr
+    global ocr1, ocr2, twopassocr, language
     import sys
 
     args = sys.argv[1:]
-    if len(args) == 3:
-        ocr1 = args[0]
-        ocr2 = args[1]
-        twopassocr = bool(int(args[2]))
-    elif len(args) == 2:
-        ocr1 = args[0]
-        ocr2 = args[1]
+    if len(args) == 4:
+        language = args[0]
+        ocr1 = args[1]
+        ocr2 = args[2]
+        twopassocr = bool(int(args[3]))
+    elif len(args) == 3:
+        language = args[0]
+        ocr1 = args[1]
+        ocr2 = args[2]
         twopassocr = True
-    elif len(args) == 1:
-        ocr1 = args[0]
+    elif len(args) == 2:
+        language = args[0]
+        ocr1 = args[1]
         ocr2 = None
         twopassocr = False
     else:
+        language = "ja"
         ocr1 = "oneocr"
         ocr2 = "glens"
         twopassocr = True

GameSentenceMiner/util.py

@@ -58,7 +58,7 @@ def timedelta_to_ffmpeg_friendly_format(td_obj):
 
 
 def get_file_modification_time(file_path):
-    mod_time_epoch = os.path.getctime(file_path)
+    mod_time_epoch = os.path.getmtime(file_path)
     mod_time = datetime.fromtimestamp(mod_time_epoch)
     return mod_time
 
@@ -255,12 +255,12 @@ os.makedirs(os.path.dirname(TEXT_REPLACEMENTS_FILE), exist_ok=True)
 
 import urllib.request
 
-if not os.path.exists(OCR_REPLACEMENTS_FILE):
-    url = "https://raw.githubusercontent.com/bpwhelan/GameSentenceMiner/refs/heads/main/electron-src/assets/ocr_replacements.json"
-    try:
-        with urllib.request.urlopen(url) as response:
-            data = response.read().decode('utf-8')
-            with open(OCR_REPLACEMENTS_FILE, 'w', encoding='utf-8') as f:
-                f.write(data)
-    except Exception as e:
-        logger.error(f"Failed to fetch JSON from {url}: {e}")
+# if not os.path.exists(OCR_REPLACEMENTS_FILE):
+#     url = "https://raw.githubusercontent.com/bpwhelan/GameSentenceMiner/refs/heads/main/electron-src/assets/ocr_replacements.json"
+#     try:
+#         with urllib.request.urlopen(url) as response:
+#             data = response.read().decode('utf-8')
+#             with open(OCR_REPLACEMENTS_FILE, 'w', encoding='utf-8') as f:
+#                 f.write(data)
+#     except Exception as e:
+#         logger.error(f"Failed to fetch JSON from {url}: {e}")

GameSentenceMiner/web/templates/utility.html

@@ -107,26 +107,30 @@
     </style>
 </head>
 <body>
+<div style="position: fixed; top: 20px; right: 20px; display: flex; gap: 10px;">
+    <button onclick="window.location.href='/textreplacements'" style="background-color: #1a73e8; color: #ffffff; border: none; padding: 10px 20px; font-size: 12px; cursor: pointer; transition: background-color 0.3s; border-radius: 5px;">
+        Text Replacements
+    </button>
+    <button id="delete-history" style="background-color: #1a73e8; color: #ffffff; border: none; padding: 10px 20px; font-size: 12px; cursor: pointer; transition: background-color 0.3s; border-radius: 5px;">
+        Clear History
+    </button>
+</div>
 <div id="initial-events">
 
 </div>
 <hr class="initial-events-separator" id="initial-events-separator" style="display: none;">
 <div id="session-events">
 
-</div>
-<div>
-    <button onclick="window.location.href='/textreplacements'" style="margin-top: 20px; background-color: #1a73e8; color: #ffffff; border: none; padding: 10px 20px; font-size: 16px; cursor: pointer; transition: background-color 0.3s; border-radius: 5px;">
-      Text Replacements
-    </button>
 </div>
 <script>
     let mainStyle = document.querySelector('head style');
+    let deleteHistoryButton = document.getElementById('delete-history');
     console.log(mainStyle);
     let displayedEventIds = new Set();
     let isTabActive = true;
     let isFetching = false; // Flag to track if a fetch is in progress
     let intervalId = 0;
-    const fetchInterval = 5000; // Define the interval as a constant
+    const fetchInterval = 100; // Define the interval as a constant
     const websocketPort = {{ websocket_port }} || 55001;
 
     // Drag selection variables
@@ -135,11 +139,13 @@
     let newCheckboxState = false;
     let hoveredCheckboxes = new Set();
     let checkboxes = []; // Will hold all checkbox elements
+    let checkboxMap = {};
     let checkboxes_being_updated = new Set();
 
     // Shift click selection variable
     let lastChecked = null;
 
+
     async function fetchEvents() {
         if (document.hidden || isFetching) {
             return;
@@ -152,21 +158,30 @@
             }
             const events = await res.json();
 
+            let historyEvents = []
             events.forEach(ev => {
                 if (!displayedEventIds.has(ev.id)) {
                     if (ev.history) {
-                        addNewEventToHistory(ev)
+                        historyEvents.push(ev);
                         document.getElementById('initial-events-separator').style.display = 'block';
                     } else {
                         addNewEvent(ev)
                     }
                 }
-                const checkbox = document.querySelector(`[data-event-id="${ev.id}"]`);
-                if (checkbox && !checkboxes_being_updated.has(ev.id)) {
-                    checkbox.checked = ev.checked;
+                if (!ev.history) {
+                    console.log(checkboxMap[ev.id])
+                    if (!checkboxes_being_updated.has(ev.id)) {
+                        const checkbox = checkboxMap[ev.id];
+                        if (checkbox) {
+                            checkbox.checked = ev.checked;
+                        }
+                    }
                 }
             });
-            checkboxes = Array.from(document.querySelectorAll('#session-events input[type="checkbox"]')); // Update checkboxes array after new events
+            if (historyEvents.length > 0) {
+                addEventsToHistory(historyEvents);
+            }
+            // checkboxes = Array.from(document.querySelectorAll('#session-events input[type="checkbox"]')); // Update checkboxes array after new events
         } catch (error) {
             console.error("Error fetching events:", error);
         } finally {
@@ -174,29 +189,32 @@
         }
     }
 
-    function addNewEventToHistory(event) {
-        displayedEventIds.add(event.id);
+    function addEventsToHistory(events) {
         const container = document.getElementById('initial-events');
-        const div = document.createElement('div');
-        // div.className = 'textline';
+        const fragment = document.createDocumentFragment();
 
-        const shadowRoot = div.attachShadow({ mode: 'open' });
+        events.forEach(event => {
+            displayedEventIds.add(event.id);
+            const div = document.createElement('div');
+            const shadowRoot = div.attachShadow({ mode: 'open' });
 
-        const wrapper = document.createElement('div');
-        wrapper.className = 'textline';
-        wrapper.innerHTML = `<p>${event.text}</p>
+            const wrapper = document.createElement('div');
+            wrapper.className = 'textline';
+            wrapper.innerHTML = `<p>${event.text}</p>
                              <em class="clock-icon">${event.time.replace(' GMT', '')}</em>
                         `;
 
-        const style = document.createElement('style');
-        style.textContent = mainStyle.innerHTML;
-        shadowRoot.appendChild(style);
-        shadowRoot.appendChild(wrapper);
+            const style = document.createElement('style');
+            style.textContent = mainStyle.innerHTML;
+            shadowRoot.appendChild(style);
+            shadowRoot.appendChild(wrapper);
 
-        container.appendChild(div);
+            fragment.appendChild(div);
+        });
+
+        container.appendChild(fragment);
         window.scrollTo({
             top: document.documentElement.scrollHeight,
-            behavior: 'smooth'
         });
     }
 
@@ -235,10 +253,13 @@
         shadowRoot.appendChild(style);
         shadowRoot.appendChild(wrapper);
 
+        let checkbox = shadowRoot.querySelector('.multi-line-checkbox')
+        checkboxes.push(checkbox);
+        checkboxMap[event.id] = checkbox; // Store the checkbox in the map for easy access
+
         container.appendChild(div);
         window.scrollTo({
             top: document.documentElement.scrollHeight,
-            behavior: 'smooth'
         });
     }
 
@@ -344,10 +365,34 @@
         lastChecked = e.target;
     }
 
+    function deleteHistory(e) {
+        e.preventDefault();
+        if (confirm("Are you sure you want to delete the history? This action cannot be undone.")) {
+            fetch('/clear_history', {
+                method: 'POST',
+                headers: { 'Content-Type': 'application/json' }
+            })
+            .then(response => {
+                if (!response.ok) {
+                    throw new Error(`HTTP error! Status: ${response.status}`);
+                }
+                // Clear the displayed events
+                displayedEventIds.clear();
+                document.getElementById('initial-events').innerHTML = '';
+                document.getElementById('session-events').innerHTML = '';
+                document.getElementById('initial-events-separator').style.display = 'none';
+            })
+            .catch(error => {
+                console.error("Error deleting history:", error);
+            });
+        }
+    }
+
     document.addEventListener('mousedown', handleMouseDown);
     document.addEventListener('mouseup', handleMouseUp);
     document.addEventListener('mouseover', handleMouseOver);
     document.addEventListener('click', handleCheckboxClick);
+    deleteHistoryButton.addEventListener('click', deleteHistory);
 
     const websocketURL = 'ws://localhost:' + websocketPort;
     let websocket = {};
@@ -404,7 +449,7 @@
         return websocket;
     };
 
-    connectWebSocket();
+    // connectWebSocket();
 
 
     fetchEvents();
@@ -419,7 +464,6 @@
 
     window.scrollTo({
         top: document.documentElement.scrollHeight,
-        behavior: 'smooth'
     });
 </script>
 </body>

GameSentenceMiner/web/texthooking_page.py

@@ -103,6 +103,10 @@ class EventManager:
         event_queue.put(new_event)
         return new_event
 
+    def reset_checked_lines(self):
+        for event in self.events:
+            event.checked = False
+
     def get_events(self):
         return self.events
 
@@ -117,6 +121,14 @@ class EventManager:
         if self.conn:
             self.conn.close()
 
+    def clear_history(self):
+        self.cursor.execute("DELETE FROM events WHERE time < ?", (initial_time.isoformat(),))
+        logger.info(f"Cleared history before {initial_time.isoformat()}")
+        self.conn.commit()
+        # Clear the in-memory events as well
+        event_manager.events = [event for event in event_manager if not event.history]
+        event_manager.events_dict = {event.id: event for event in event_manager.events}
+
 class EventProcessor(threading.Thread):
     def __init__(self, event_queue, db_path):
         super().__init__()
@@ -227,6 +239,13 @@ def textreplacements():
 def get_data():
     return jsonify([event.to_dict() for event in event_manager])
 
+@app.route('/clear_history', methods=['POST'])
+def clear_history():
+    temp_em = EventManager()
+    temp_em.clear_history()
+    temp_em.close_connection()
+    return jsonify({'message': 'History cleared successfully'}), 200
+
 
 async def add_event_to_texthooker(line: GameLine):
     logger.info("Adding event to web server: %s", line.text)
@@ -248,8 +267,7 @@ def update_event():
         return jsonify({'error': 'Missing id or checked status'}), 400
 
     event_manager.get(event_id).checked = checked
-
-    return jsonify({'error': 'Event not found'}), 404
+    return jsonify({'message': 'Event updated successfully'}), 200
 
 @app.route('/get-screenshot', methods=['Post'])
 def get_screenshot():
@@ -339,8 +357,7 @@ def are_lines_selected():
     return any(item.checked for item in event_manager)
 
 def reset_checked_lines():
-    for item in event_manager:
-        item.checked = False
+    event_manager.reset_checked_lines()
 
 def open_texthooker():
     webbrowser.open(url + '/texthooker')

{gamesentenceminer-2.8.13.dist-info → gamesentenceminer-2.8.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: GameSentenceMiner
-Version: 2.8.13
+Version: 2.8.15
 Summary: A tool for mining sentences from games. Update: Multi-Line Mining! Fixed!
 Author-email: Beangate <bpwhelan95@gmail.com>
 License: MIT License

{gamesentenceminer-2.8.13.dist-info → gamesentenceminer-2.8.15.dist-info}/RECORD

@@ -1,17 +1,17 @@
 GameSentenceMiner/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-GameSentenceMiner/anki.py,sha256=pSkf-il17vKZIBt1ZHHDMfvfO9M-GdF1zox-c--KkAY,14208
-GameSentenceMiner/config_gui.py,sha256=6TkDLW-0SPWMeNAwzb5WT7aVJ8mxPqmhAQcS1BHzTik,70979
-GameSentenceMiner/configuration.py,sha256=rxl0YocwAF8cCBakOl7k2CPpOfL3FZxnsGMlKZOezmc,21876
+GameSentenceMiner/anki.py,sha256=OCLgZa-iEp93v-R0zKFkDCjule_EAoP5rIqtnMHLnOw,14226
+GameSentenceMiner/config_gui.py,sha256=-xZRTzFtnhnmbSiL03XpNrzV29Pb891nLuXHI_CZw7I,73759
+GameSentenceMiner/configuration.py,sha256=-De0KfXu0jHTPl0xyktUxT-_fNUS_AK7nmzblKXRdGc,22525
 GameSentenceMiner/electron_config.py,sha256=dGcPYCISPehXubYSzsDuI2Gl092MYK0u3bTnkL9Jh1Y,9787
-GameSentenceMiner/ffmpeg.py,sha256=mcEcJnYl06oJGbLaymFUfqClFiHf6Hhf2SXo3UV9tvM,13378
-GameSentenceMiner/gametext.py,sha256=ClSpOeohBWG17MRVIbhXfNDnkUdxU9mTspGv9975uEc,5422
-GameSentenceMiner/gsm.py,sha256=vCEPg7rE68AUD2u6DesjLxuZSy1gJzbiA0fig673WRM,25254
+GameSentenceMiner/ffmpeg.py,sha256=lLZ9v8_h5wfenLC6W36Ikt0Q7HQrChxsZ6lPk2umXjI,14658
+GameSentenceMiner/gametext.py,sha256=pyIjMxMgKAAIyKzvtq8FV-zdg1ETRf7GVgkE19_2-B4,5513
+GameSentenceMiner/gsm.py,sha256=bwDt7yAM9_Jf0BY0oxs6vwL8jGrHxnw_sznqbJp5Hdg,25382
 GameSentenceMiner/model.py,sha256=JdnkT4VoPOXmOpRgFdvERZ09c9wLN6tUJxdrKlGZcqo,5305
 GameSentenceMiner/notification.py,sha256=FY39ChSRK0Y8TQ6lBGsLnpZUFPtFpSy2tweeXVoV7kc,2809
 GameSentenceMiner/obs.py,sha256=GPlsFrcv1eYelXyJfpspGK0iZK5AXPkoFsIGdB7eJrk,10002
 GameSentenceMiner/package.py,sha256=YlS6QRMuVlm6mdXx0rlXv9_3erTGS21jaP3PNNWfAH0,1250
 GameSentenceMiner/text_log.py,sha256=tBuZ8ElUgPtiQV8U6U90kmRxposwIkL3fjOYejdzikc,5153
-GameSentenceMiner/util.py,sha256=bb75EQdk4Nf0i9t3XMznjd6NxTWfkOVeE5bZFstbCbU,8910
+GameSentenceMiner/util.py,sha256=LzWGIDZb8NLv-RyrE_d6ycoQEwM1zpaDhWp0LKb6_Zc,8928
 GameSentenceMiner/ai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 GameSentenceMiner/ai/ai_prompting.py,sha256=uTtXIDRpcQqPT4EC-R_pwRP9pBmZ64I6vMDOexhJRp8,9505
 GameSentenceMiner/communication/__init__.py,sha256=_jGn9PJxtOAOPtJ2rI-Qu9hEHVZVpIvWlxKvqk91_zI,638
@@ -22,10 +22,10 @@ GameSentenceMiner/downloader/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 GameSentenceMiner/downloader/download_tools.py,sha256=mI1u_FGBmBqDIpCH3jOv8DOoZ3obgP5pIf9o9SVfX2Q,8131
 GameSentenceMiner/downloader/oneocr_dl.py,sha256=o3ANp5IodEQoQ8GPcJdg9Y8JzA_lictwnebFPwwUZVk,10144
 GameSentenceMiner/ocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-GameSentenceMiner/ocr/gsm_ocr_config.py,sha256=zagsB4UD9mmZX_r6dFBCXZqdDa0XGk-RvIqbKoPB9lQ,1932
+GameSentenceMiner/ocr/gsm_ocr_config.py,sha256=rQC6C8PKJXWoAvwCOYa363kodQQBwl1YNeYsD0bBbx4,1957
 GameSentenceMiner/ocr/ocrconfig.py,sha256=_tY8mjnzHMJrLS8E5pHqYXZjMuLoGKYgJwdhYgN-ny4,6466
 GameSentenceMiner/ocr/owocr_area_selector.py,sha256=gwYOz-fA5qoL63wh77eyGJtBtO7YVvWyO5cHb3D0Oz4,46738
-GameSentenceMiner/ocr/owocr_helper.py,sha256=PCsPbqrECSbi4u8NIq3PJotStaYVBBbfccHu-DrqpwU,17269
+GameSentenceMiner/ocr/owocr_helper.py,sha256=-ezF6AO7ayZBs2vMt0Zj7D-gc8YbrgO69mFsJD7VmRs,17383
 GameSentenceMiner/owocr/owocr/__init__.py,sha256=opjBOyGGyEqZCE6YdZPnyt7nVfiwyELHsXA0jAsjm14,25
 GameSentenceMiner/owocr/owocr/__main__.py,sha256=r8MI6RAmbkTWqOJ59uvXoDS7CSw5jX5war9ULGWELrA,128
 GameSentenceMiner/owocr/owocr/config.py,sha256=n-xtVylb2Q_H84jb1ZsIGxPQjTNnyvnRny1RhtaLJM8,7550
@@ -38,7 +38,7 @@ GameSentenceMiner/vad/silero_trim.py,sha256=ULf3zwS-JMsY82cKF7gZxREHw8L6lgpWF2U1
 GameSentenceMiner/vad/vosk_helper.py,sha256=125X8C9NxFPlWWpoNsbOnEqKx8RCjXN109zNx_QXhyg,6070
 GameSentenceMiner/vad/whisper_helper.py,sha256=JJ-iltCh813XdjyEw0Wn5DaErf6PDqfH0Efu1Md8cIY,3543
 GameSentenceMiner/web/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-GameSentenceMiner/web/texthooking_page.py,sha256=Xf-m_bNSPUNO5x1u4sYdEtHx6ERF8IXrkF9wDx9pto8,12791
+GameSentenceMiner/web/texthooking_page.py,sha256=AtVV9RS7HC3XnOq4X0FIMqJrzFoGlfSHFvS_CfhuzuA,13558
 GameSentenceMiner/web/static/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 GameSentenceMiner/web/static/apple-touch-icon.png,sha256=OcMI8af_68DA_tweOsQ5LytTyMwm7-hPW07IfrOVgEs,46132
 GameSentenceMiner/web/static/favicon-96x96.png,sha256=lOePzjiKl1JY2J1kT_PMdyEnrlJmi5GWbmXJunM12B4,16502
@@ -50,10 +50,10 @@ GameSentenceMiner/web/static/web-app-manifest-192x192.png,sha256=EfSNnBmsSaLfESb
 GameSentenceMiner/web/static/web-app-manifest-512x512.png,sha256=wyqgCWCrLEUxSRXmaA3iJEESd-vM-ZmlTtZFBY4V8Pk,230819
 GameSentenceMiner/web/templates/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 GameSentenceMiner/web/templates/text_replacements.html,sha256=tV5c8mCaWSt_vKuUpbdbLAzXZ3ATZeDvQ9PnnAfqY0M,8598
-GameSentenceMiner/web/templates/utility.html,sha256=8yJvmHqkHoMN06qWDckhGoguWyP7LUVZ2oms0tBRdEw,14297
-gamesentenceminer-2.8.13.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-gamesentenceminer-2.8.13.dist-info/METADATA,sha256=EGC_NS8I5l3YuHp0Sd9TaUyVfp_9u3NkZboAZqsAxvM,5933
-gamesentenceminer-2.8.13.dist-info/WHEEL,sha256=ooBFpIzZCPdw3uqIQsOo4qqbA4ZRPxHnOH7peeONza0,91
-gamesentenceminer-2.8.13.dist-info/entry_points.txt,sha256=2APEP25DbfjSxGeHtwBstMH8mulVhLkqF_b9bqzU6vQ,65
-gamesentenceminer-2.8.13.dist-info/top_level.txt,sha256=V1hUY6xVSyUEohb0uDoN4UIE6rUZ_JYx8yMyPGX4PgQ,18
-gamesentenceminer-2.8.13.dist-info/RECORD,,
+GameSentenceMiner/web/templates/utility.html,sha256=NUp4Yjs6_j7YeqsM2rcF0LzwS6nXSBUWJDl-k2E8BbM,16270
+gamesentenceminer-2.8.15.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+gamesentenceminer-2.8.15.dist-info/METADATA,sha256=bLKHdjfoOke5LB1zD8IerMRtf_WvCAaAsSGtUxcg-Us,5933
+gamesentenceminer-2.8.15.dist-info/WHEEL,sha256=GHB6lJx2juba1wDgXDNlMTyM13ckjBMKf-OnwgKOCtA,91
+gamesentenceminer-2.8.15.dist-info/entry_points.txt,sha256=2APEP25DbfjSxGeHtwBstMH8mulVhLkqF_b9bqzU6vQ,65
+gamesentenceminer-2.8.15.dist-info/top_level.txt,sha256=V1hUY6xVSyUEohb0uDoN4UIE6rUZ_JYx8yMyPGX4PgQ,18
+gamesentenceminer-2.8.15.dist-info/RECORD,,

{gamesentenceminer-2.8.13.dist-info → gamesentenceminer-2.8.15.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.0.1)
+Generator: setuptools (80.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any