GameSentenceMiner 2.17.3__py3-none-any.whl → 2.17.5__py3-none-any.whl

GameSentenceMiner/ocr/owocr_helper.py

@@ -199,25 +199,30 @@ rectangles = None
 last_ocr2_result = []
 last_sent_result = ""
 
-def do_second_ocr(ocr1_text, time, img, filtering, pre_crop_image=None, ignore_furigana_filter=False, ignore_previous_result=False):
-    global twopassocr, ocr2, last_ocr2_result, last_sent_result
-    try:
-        orig_text, text = run.process_and_write_results(img, None, last_ocr2_result if not ignore_previous_result else None, filtering, None,
-                                                        engine=get_ocr_ocr2(), furigana_filter_sensitivity=furigana_filter_sensitivity if not ignore_furigana_filter else 0)
-        
-        if compare_ocr_results(last_sent_result, text, threshold=80):
-            if text:
-                logger.info("Seems like Text we already sent, not doing anything.")
-            return
-        save_result_image(img, pre_crop_image=pre_crop_image)
-        last_ocr2_result = orig_text
-        last_sent_result = text
-        asyncio.run(send_result(text, time))
-    except json.JSONDecodeError:
-        print("Invalid JSON received.")
-    except Exception as e:
-        logger.exception(e)
-        print(f"Error processing message: {e}")
+class OCRProcessor():
+    def __init__(self):
+        self.filtering = TextFiltering(lang=get_ocr_language())
+        pass
+
+    def do_second_ocr(self, ocr1_text, time, img, filtering, pre_crop_image=None, ignore_furigana_filter=False, ignore_previous_result=False):
+        global twopassocr, ocr2, last_ocr2_result, last_sent_result
+        try:
+            orig_text, text = run.process_and_write_results(img, None, last_ocr2_result if not ignore_previous_result else None, self.filtering, None,
+                                                            engine=get_ocr_ocr2(), furigana_filter_sensitivity=furigana_filter_sensitivity if not ignore_furigana_filter else 0)
+            
+            if compare_ocr_results(last_sent_result, text, threshold=80):
+                if text:
+                    logger.info("Seems like Text we already sent, not doing anything.")
+                return
+            save_result_image(img, pre_crop_image=pre_crop_image)
+            last_ocr2_result = orig_text
+            last_sent_result = text
+            asyncio.run(send_result(text, time))
+        except json.JSONDecodeError:
+            print("Invalid JSON received.")
+        except Exception as e:
+            logger.exception(e)
+            print(f"Error processing message: {e}")
 
 
 def save_result_image(img, pre_crop_image=None):
@@ -249,6 +254,7 @@ previous_img = None
 previous_orig_text = ""  # Store original text result
 TEXT_APPEARENCE_DELAY = get_ocr_scan_rate() * 1000 + 500  # Adjust as needed
 force_stable = False
+second_ocr_processor = OCRProcessor()
 
 class ConfigChangeCheckThread(threading.Thread):
     def __init__(self):
@@ -461,7 +467,7 @@ def get_ocr2_image(crop_coords, og_image: Image.Image, ocr2_engine=None):
 
     # If no crop or optimization, just apply config and return
     if not crop_coords or not get_ocr_optimize_second_scan():
-        img = run.apply_ocr_config_to_image(img, ocr_config_local, is_secondary=True)
+        img = run.apply_ocr_config_to_image(img, ocr_config_local, is_secondary=False)
         return img
 
     # Calculate scaling ratios
@@ -495,7 +501,7 @@ def process_task_queue():
             if task is None:  # Exit signal
                 break
             ocr1_text, stable_time, previous_img_local, filtering, pre_crop_image = task
-            do_second_ocr(ocr1_text, stable_time, previous_img_local, filtering, pre_crop_image)
+            second_ocr_processor.do_second_ocr(ocr1_text, stable_time, previous_img_local, filtering, pre_crop_image)
         except Exception as e:
             logger.exception(f"Error processing task: {e}")
         finally:
@@ -550,21 +556,21 @@ def add_ss_hotkey(ss_hotkey="ctrl+shift+g"):
         ocr_config.scale_to_custom_size(img.width, img.height)
         for rectangle in [rectangle for rectangle in ocr_config.rectangles if rectangle.is_secondary]:
             new_img = run.apply_ocr_config_to_image(img, ocr_config, is_secondary=True, rectangles=[rectangle])
-            do_second_ocr("", datetime.now(), new_img, TextFiltering(lang=get_ocr_language()), ignore_furigana_filter=True, ignore_previous_result=True)
+            second_ocr_processor.do_second_ocr("", datetime.now(), new_img, TextFiltering(lang=get_ocr_language()), ignore_furigana_filter=True, ignore_previous_result=True)
 
     filtering = TextFiltering(lang=get_ocr_language())
     cropper = ScreenCropper()
     def capture():
         print("Taking screenshot...")
         img = cropper.run()
-        do_second_ocr("", datetime.now(), img, filtering, ignore_furigana_filter=True, ignore_previous_result=True)
+        second_ocr_processor.do_second_ocr("", datetime.now(), img, filtering, ignore_furigana_filter=True, ignore_previous_result=True)
     def capture_main_monitor():
         print("Taking screenshot of main monitor...")
         with mss.mss() as sct:
             main_monitor = sct.monitors[1] if len(sct.monitors) > 1 else sct.monitors[0]
             img = sct.grab(main_monitor)
             img_bytes = mss.tools.to_png(img.rgb, img.size)
-            do_second_ocr("", datetime.now(), img_bytes, filtering, ignore_furigana_filter=True, ignore_previous_result=True)
+            second_ocr_processor.do_second_ocr("", datetime.now(), img_bytes, filtering, ignore_furigana_filter=True, ignore_previous_result=True)
     hotkey_reg = None
     secondary_hotkey_reg = None
     try:

GameSentenceMiner/owocr/owocr/ocr.py

@@ -375,7 +375,7 @@ class GoogleLens:
                     # logger.info(f"Vertical space: {vertical_space}, Average height: {avg_height}")
                     # logger.info(avg_height * 2)
                     if vertical_space > avg_height * 2:
-                        res += 'BLANK_LINE'
+                        res += 'BLANK_LINE\n'
                 for line in paragraph['lines']:
                     if furigana_filter_sensitivity:
                         line_width = line['geometry']['bounding_box']['width'] * img.width

GameSentenceMiner/owocr/owocr/run.py

@@ -320,13 +320,20 @@ class RequestHandler(socketserver.BaseRequestHandler):
             conn.sendall(b'False')
 
 
+class PassthroughSegmenter:
+    def segment(self, text):
+        return [text]
+
 class TextFiltering:
     accurate_filtering = False
 
     def __init__(self, lang='ja'):
-        from pysbd import Segmenter
+        from pysbd import Segmenter, languages
         self.initial_lang = get_ocr_language() or lang
-        self.segmenter = Segmenter(language=get_ocr_language(), clean=True)
+        if lang in languages.LANGUAGE_CODES:
+            self.segmenter = Segmenter(language=lang, clean=True)
+        else:
+            self.segmenter = PassthroughSegmenter()
         self.kana_kanji_regex = re.compile(
             r'[\u3041-\u3096\u30A1-\u30FA\u4E00-\u9FFF]')
         self.chinese_common_regex = re.compile(r'[\u4E00-\u9FFF]')
@@ -371,8 +378,11 @@ class TextFiltering:
     def __call__(self, text, last_result, engine=None, is_second_ocr=False):
         lang = get_ocr_language()
         if self.initial_lang != lang:
-            from pysbd import Segmenter
-            self.segmenter = Segmenter(language=get_ocr_language(), clean=True)
+            from pysbd import Segmenter, languages
+            if lang in languages.LANGUAGE_CODES:
+                self.segmenter = Segmenter(language=lang, clean=True)
+            else:
+                self.segmenter = PassthroughSegmenter()
             self.initial_lang = get_ocr_language()
 
         orig_text = self.segmenter.segment(text)

{gamesentenceminer-2.17.3.dist-info → gamesentenceminer-2.17.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: GameSentenceMiner
-Version: 2.17.3
+Version: 2.17.5
 Summary: A tool for mining sentences from games. Update: Overlay?
 Author-email: Beangate <bpwhelan95@gmail.com>
 License: MIT License
@@ -18,7 +18,7 @@ Requires-Dist: DateTime~=5.5
 Requires-Dist: pyperclip~=1.9.0
 Requires-Dist: soundfile~=0.12.1
 Requires-Dist: toml~=0.10.2
-Requires-Dist: psutil~=6.0.0
+Requires-Dist: psutil~=7.1.0
 Requires-Dist: rapidfuzz~=3.9.7
 Requires-Dist: plyer~=2.1.0
 Requires-Dist: keyboard~=0.13.5

{gamesentenceminer-2.17.3.dist-info → gamesentenceminer-2.17.5.dist-info}/RECORD

@@ -22,14 +22,14 @@ GameSentenceMiner/ocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
 GameSentenceMiner/ocr/gsm_ocr_config.py,sha256=Ov04c-nKzh3sADxO-5JyZWVe4DlrHM9edM9tc7-97Jo,5970
 GameSentenceMiner/ocr/ocrconfig.py,sha256=_tY8mjnzHMJrLS8E5pHqYXZjMuLoGKYgJwdhYgN-ny4,6466
 GameSentenceMiner/ocr/owocr_area_selector.py,sha256=4MjItlaZ78Smxa3uxMxbjU0n2z_IBTG-iBpDB9COSL8,29270
-GameSentenceMiner/ocr/owocr_helper.py,sha256=kuwEiOOyOMHDdsDboyDqB_MI8WL9bsN9XubACfgw1KQ,32036
+GameSentenceMiner/ocr/owocr_helper.py,sha256=BGBiMDziPknCSj2VM4kpVL3iCtIswbisiPuiPOAVqjs,32370
 GameSentenceMiner/ocr/ss_picker.py,sha256=0IhxUdaKruFpZyBL-8SpxWg7bPrlGpy3lhTcMMZ5rwo,5224
 GameSentenceMiner/owocr/owocr/__init__.py,sha256=87hfN5u_PbL_onLfMACbc0F5j4KyIK9lKnRCj6oZgR0,49
 GameSentenceMiner/owocr/owocr/__main__.py,sha256=XQaqZY99EKoCpU-gWQjNbTs7Kg17HvBVE7JY8LqIE0o,157
 GameSentenceMiner/owocr/owocr/config.py,sha256=qM7kISHdUhuygGXOxmgU6Ef2nwBShrZtdqu4InDCViE,8103
 GameSentenceMiner/owocr/owocr/lens_betterproto.py,sha256=oNoISsPilVVRBBPVDtb4-roJtAhp8ZAuFTci3TGXtMc,39141
-GameSentenceMiner/owocr/owocr/ocr.py,sha256=vRTMKLzi6GDBFZWCyf0tYi6es3cP1cvQOBjZqaZmnBg,70482
-GameSentenceMiner/owocr/owocr/run.py,sha256=bIXC_7PltyVvlA8beCVqdLcKVai8LvVHBRqEueq2GkQ,81545
+GameSentenceMiner/owocr/owocr/ocr.py,sha256=7VCTBl4-8mO9P73olLMihUFtu3idBdyZIWP6XQhCte4,70484
+GameSentenceMiner/owocr/owocr/run.py,sha256=Z7VkoFrsoQbMTHc6CmwpcMzsOROK9A_RJRwhlxw15oA,81871
 GameSentenceMiner/owocr/owocr/screen_coordinate_picker.py,sha256=Na6XStbQBtpQUSdbN3QhEswtKuU1JjReFk_K8t5ezQE,3395
 GameSentenceMiner/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 GameSentenceMiner/tools/audio_offset_selector.py,sha256=8Stk3BP-XVIuzRv9nl9Eqd2D-1yD3JrgU-CamBywJmY,8542
@@ -90,9 +90,9 @@ GameSentenceMiner/web/templates/utility.html,sha256=KtqnZUMAYs5XsEdC9Tlsd40NKAVi
 GameSentenceMiner/web/templates/components/navigation.html,sha256=6y9PvM3nh8LY6JWrZb6zVOm0vqkBLDc6d3gB9X5lT_w,1055
 GameSentenceMiner/web/templates/components/theme-styles.html,sha256=hiq3zdJljpRjQO1iUA7gfFKwXebltG-IWW-gnKS4GHA,3439
 GameSentenceMiner/wip/__init___.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gamesentenceminer-2.17.3.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-gamesentenceminer-2.17.3.dist-info/METADATA,sha256=Yr9TwKuUOUhU5QWe2dqwq9DPkfpvGZl7OE9D1NLZZe8,7348
-gamesentenceminer-2.17.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-gamesentenceminer-2.17.3.dist-info/entry_points.txt,sha256=2APEP25DbfjSxGeHtwBstMH8mulVhLkqF_b9bqzU6vQ,65
-gamesentenceminer-2.17.3.dist-info/top_level.txt,sha256=V1hUY6xVSyUEohb0uDoN4UIE6rUZ_JYx8yMyPGX4PgQ,18
-gamesentenceminer-2.17.3.dist-info/RECORD,,
+gamesentenceminer-2.17.5.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+gamesentenceminer-2.17.5.dist-info/METADATA,sha256=CUChAokaBSIh9jkDR4ICjwvQIdj8MqLAeVlyqHKsZGM,7348
+gamesentenceminer-2.17.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+gamesentenceminer-2.17.5.dist-info/entry_points.txt,sha256=2APEP25DbfjSxGeHtwBstMH8mulVhLkqF_b9bqzU6vQ,65
+gamesentenceminer-2.17.5.dist-info/top_level.txt,sha256=V1hUY6xVSyUEohb0uDoN4UIE6rUZ_JYx8yMyPGX4PgQ,18
+gamesentenceminer-2.17.5.dist-info/RECORD,,