Skip to content
Navigation Menu
{{ message }}
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathmain_controller.py
More file actions
1300 lines (1148 loc) · 50.1 KB
/
Copy pathmain_controller.py
File metadata and controls
1300 lines (1148 loc) · 50.1 KB
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import json
from pathlib import Path
import tempfile
from datetime import datetime
from xml.sax.saxutils import escape
from loguru import logger
from PyQt6.QtCore import QObject, Qt, QThread, QUrl
from PyQt6.QtGui import QDesktopServices
from PyQt6.QtWidgets import (
QApplication,
QFileDialog,
QInputDialog,
QListWidgetItem,
QMenu,
QMessageBox,
QWidget,
)
try:
from PyQt6.QtMultimedia import QAudioOutput, QMediaPlayer
except ImportError: # pragma: no cover - optional multimedia backend
QAudioOutput = None
QMediaPlayer = None
from app.controller.background_workers import (
BatchExportWorker,
DocumentParseWorker,
build_provider_input,
build_provider_metadata,
build_ssml_document,
sanitize_batch_name,
)
from app.controller.second_controller import SecondController
from app.controller.settings_controller import SettingsController
from app.gui.second_window import SecondApp
from app.gui.setup_guide_dialog import SetupGuideDialog
from app.model.app_settings import AppSettings
from app.model.processors.tts_processor import TTSProcessor
from app.model.scraper.document_scraper import DocumentScraper
from app.model.ssml.ssml_config import SSMLConfig
from app.model.tts_providers import (
get_provider_display_name,
get_provider_profile,
resolve_tts_provider_config,
)
from app.utils.logging_config import configure_logging
from app.utils.resources import resource_path
from app.utils.text_cleaner import TextCleaner
class MainController(QObject):
SETTINGS_PATH = Path("data/dynamic/app_settings.json")
AUDIO_HISTORY_PATH = Path("data/dynamic/audio_history.json")
MAX_HISTORY_ITEMS = 10
HISTORY_SETTINGS_FIELDS = (
"tts_provider",
"voice",
"speaking_rate",
"synthesis_volume",
"emphasis_level",
"pitch",
"pitch_range",
"pause_duration",
"pause_position",
"auto_clean_text",
"gemini_model",
"gemini_language_code",
"gemini_style_prompt",
"gemini_config_path",
"local_tts_driver_name",
"local_tts_config_path",
"polly_engine",
"polly_config_path",
"output_dir",
)
def __init__(self, view):
super().__init__()
self.view = view
self.cleaner = TextCleaner()
self.settings = AppSettings.load(self.SETTINGS_PATH)
self.voice_config = SSMLConfig()
self.document_scraper = DocumentScraper()
self.tts_processor = None
self.settings_controller = SettingsController(self.view)
self.second_window = None
self.second_controller = None
self.setup_guide_dialog = None
self.latest_audio_path = None
self.preview_audio_path = None
self.playing_history_audio_path = None
self.audio_output = None
self.media_player = None
self.document_parse_thread = None
self.document_parse_worker = None
self.document_parse_path = None
self.batch_export_thread = None
self.batch_export_worker = None
self.batch_export_active = False
self._updating_ui_state = False
self.audio_history = self._load_audio_history()
self._setup_media_backend()
self._connect_signals()
self._refresh_ui_state()
self._refresh_history_panel()
self.update_ssml_preview()
self._surface_document_dependency_status()
logger.info("Main controller initialized.")
def _setup_media_backend(self):
if QMediaPlayer is None or QAudioOutput is None:
return
self.audio_output = QAudioOutput()
self.media_player = QMediaPlayer()
self.media_player.setAudioOutput(self.audio_output)
self.audio_output.setVolume(self.settings.playback_volume / 100)
def _connect_signals(self):
self.view.openSecondWindowButton.clicked.connect(self.open_second_window)
self.view.openSettingsButton.clicked.connect(self.toggle_settings_sidebar)
self.view.previewButton.clicked.connect(self.update_ssml_preview)
self.view.cleanTextButton.clicked.connect(self.clean_text)
self.view.playButton.clicked.connect(self.generate_and_play_audio)
self.view.generateButton.clicked.connect(self.export_audio_file)
self.view.stopButton.clicked.connect(self.stop_audio)
self.view.cancelTaskButton.clicked.connect(self.cancel_background_work)
self.view.applyNarrationButton.clicked.connect(
self.apply_narration_to_selection
)
self.view.playbackVolumeSlider.valueChanged.connect(
self.update_playback_volume
)
self.view.actionOpenText.triggered.connect(self.open_document_file)
self.view.actionOpenUrl.triggered.connect(self.open_url_source)
self.view.actionOpenRawHtml.triggered.connect(self.open_raw_html_source)
self.view.actionExportEditorText.triggered.connect(self.export_editor_text)
self.view.actionExportAudio.triggered.connect(self.export_audio_file)
self.view.actionExit.triggered.connect(self.view.close)
self.view.actionSettings.triggered.connect(self.toggle_settings_sidebar)
self.view.actionOpenScraper.triggered.connect(self.open_second_window)
self.view.actionSetupGuide.triggered.connect(self.open_setup_guide)
self.view.actionAbout.triggered.connect(self.show_about)
self.view.textEdit.textChanged.connect(self._handle_editor_text_changed)
self.view.historyList.itemDoubleClicked.connect(
self.play_selected_history_audio
)
self.view.historyList.customContextMenuRequested.connect(
self.show_history_context_menu
)
self.view.historyToggleButton.clicked.connect(self.toggle_recent_audio)
self.view.applySidebarSettingsButton.clicked.connect(
self.apply_sidebar_settings
)
self.view.collapseSettingsSidebarButton.clicked.connect(
self.hide_settings_sidebar
)
def _sanitize_batch_name(self, value):
return sanitize_batch_name(value)
def _refresh_ui_state(self):
self._updating_ui_state = True
self.view.outputStatusLabel.setText(
" | ".join(
(
f"Provider: {self._provider_display_name()}",
f"Voice: {self.settings.voice}",
f"Rate: {self.settings.speaking_rate}",
f"Speech Volume: {self.settings.synthesis_volume}",
f"Output: {self.settings.output_dir}",
)
)
)
self.view.playbackVolumeSlider.setValue(self.settings.playback_volume)
self.view.playbackVolumeValueLabel.setText(
f"{self.settings.playback_volume}%"
)
self.view.sidebarSettingsEditor.set_settings(self.settings)
self._refresh_action_states()
provider_config = self._resolve_tts_provider_config()
if provider_config is not None:
self.view.statusbar.showMessage("Ready")
else:
provider_name = self._provider_display_name()
self.view.statusbar.showMessage(
f"Ready, but {provider_name} is not configured."
)
self._updating_ui_state = False
def _surface_document_dependency_status(self):
dependency_message = self.document_scraper.dependency_status_message()
if not dependency_message:
return
logger.warning("Document parser dependency check: {}", dependency_message)
self.view.statusbar.showMessage(
"Some import formats are unavailable. Run `poetry install` to install all parser dependencies."
)
def _current_editor_text(self):
return self.view.textEdit.toPlainText().strip()
def _set_inline_hint(self, text):
self.view.actionHintLabel.setText(text)
def apply_narration_to_selection(self):
cursor = self.view.textEdit.textCursor()
selected_text = cursor.selectedText().replace("\u2029", "\n")
if not selected_text.strip():
selected_text = "Narration text"
attributes = []
speaker = self.view.narrationSpeakerEdit.text().strip()
voice = self.view.narrationVoiceCombo.currentText().strip()
rate = self.view.narrationRateCombo.currentText().strip()
volume = self.view.narrationVolumeCombo.currentText().strip()
pause = self.view.narrationPauseCombo.currentText().strip()
if speaker:
attributes.append(f'speaker="{self._narration_attribute_value(speaker)}"')
if voice:
attributes.append(f'voice="{self._narration_attribute_value(voice)}"')
if rate and rate != "default":
attributes.append(f'rate="{self._narration_attribute_value(rate)}"')
if volume and volume != "default":
attributes.append(
f'volume="{self._narration_attribute_value(volume)}"'
)
if pause and pause != "none":
attributes.append(f'pause="{self._narration_attribute_value(pause)}"')
attribute_text = f" {' '.join(attributes)}" if attributes else ""
cursor.insertText(
f"[[narration{attribute_text}]]{selected_text}[[/narration]]"
)
self.view.textEdit.setTextCursor(cursor)
self.update_ssml_preview()
self.view.statusbar.showMessage(
"Applied narration settings to the selected text."
)
logger.info("Applied narration markup to selected editor text.")
def _narration_attribute_value(self, value):
return str(value).replace('"', "'").strip()
def _refresh_action_states(self):
has_text = bool(self._current_editor_text())
provider_profile = get_provider_profile(
getattr(self.settings, "tts_provider", "azure")
)
multimedia_available = (
self.media_player is not None and self.audio_output is not None
)
has_preview_audio = bool(
self.preview_audio_path
or self.__dict__.get("playing_history_audio_path")
)
background_work_active = self.__dict__.get("batch_export_active", False) or (
self.__dict__.get("document_parse_thread") is not None
)
self.view.previewButton.setEnabled(
has_text and provider_profile.supports_ssml
)
self.view.cleanTextButton.setEnabled(has_text)
self.view.playButton.setEnabled(has_text)
self.view.generateButton.setEnabled(has_text)
self.view.actionExportAudio.setEnabled(has_text)
self.view.stopButton.setEnabled(multimedia_available and has_preview_audio)
self.view.playbackVolumeSlider.setEnabled(multimedia_available)
self.view.cancelTaskButton.setEnabled(background_work_active)
if provider_profile.supports_ssml:
self.view.previewButton.setText("Preview SSML")
self.view.previewButton.setToolTip(
"Render the provider-ready SSML document used for synthesis."
)
else:
self.view.previewButton.setText("Preview Unavailable")
self.view.previewButton.setToolTip(
f"{self._provider_display_name()} does not expose an SSML preview."
)
if multimedia_available:
self.view.playButton.setText("Generate && Play")
self.view.playButton.setToolTip(
"Generate speech and play it immediately."
)
else:
self.view.playButton.setText("Generate Preview File")
self.view.playButton.setToolTip(
"Generate a preview file. Live playback is unavailable in this environment."
)
if background_work_active:
self.view.previewButton.setEnabled(False)
self.view.cleanTextButton.setEnabled(False)
self.view.playButton.setEnabled(False)
self.view.generateButton.setEnabled(False)
self.view.actionExportAudio.setEnabled(False)
self.view.stopButton.setEnabled(False)
self.view.openSecondWindowButton.setEnabled(False)
self._set_inline_hint(
"Background work is running. Use Cancel Task if you need to stop it."
)
return
self.view.openSecondWindowButton.setEnabled(True)
if not has_text:
self._set_inline_hint(
"Type or import text to enable preview and generation actions."
)
return
if not provider_profile.supports_ssml:
provider_name = self._provider_display_name()
if not multimedia_available:
self._set_inline_hint(
f"{provider_name} uses provider-controlled text synthesis instead of SSML. Preview is unavailable, and playback controls are disabled because multimedia support is unavailable."
)
elif has_preview_audio:
self._set_inline_hint(
f"Preview audio is ready. {provider_name} uses provider-controlled text synthesis instead of SSML."
)
else:
self._set_inline_hint(
f"{provider_name} uses provider-controlled text synthesis instead of SSML. Generate audio to test the current provider settings."
)
return
advanced_chunks = []
if self.settings.emphasis_level != "none":
advanced_chunks.append(f"emphasis={self.settings.emphasis_level}")
if self.settings.pitch != "default":
advanced_chunks.append(f"pitch={self.settings.pitch}")
if self.settings.pitch_range != "default":
advanced_chunks.append(f"range={self.settings.pitch_range}")
if self.settings.pause_duration != "none":
advanced_chunks.append(
f"pause={self.settings.pause_duration} ({self.settings.pause_position})"
)
advanced_summary = (
", ".join(advanced_chunks)
if advanced_chunks
else "default advanced SSML settings"
)
if not multimedia_available:
self._set_inline_hint(
f"Text is ready and using {advanced_summary}. Preview generation works, but playback controls are disabled because multimedia support is unavailable."
)
elif has_preview_audio:
self._set_inline_hint(
f"Preview audio is ready. Current SSML uses {advanced_summary}."
)
else:
self._set_inline_hint(
f"Text is ready. Current SSML uses {advanced_summary}."
)
def _handle_editor_text_changed(self):
self._refresh_action_states()
self.update_ssml_preview()
def _load_audio_history(self):
if not self.AUDIO_HISTORY_PATH.exists():
return []
try:
with open(self.AUDIO_HISTORY_PATH, "r", encoding="utf-8") as file:
data = json.load(file)
except (OSError, json.JSONDecodeError) as error:
logger.warning("Unable to load audio history: {}", error)
return []
if not isinstance(data, list):
return []
cleaned_history = []
for entry in data:
if not isinstance(entry, dict):
continue
cleaned_history.append(
{
"filename": str(entry.get("filename", "")),
"output_path": str(entry.get("output_path", "")),
"voice": str(entry.get("voice", self.settings.voice)),
"generated_at": str(entry.get("generated_at", "")),
"source": str(entry.get("source", "export")),
"source_text": str(entry.get("source_text", "")),
"settings": dict(entry.get("settings") or {}),
}
)
return cleaned_history[: self.MAX_HISTORY_ITEMS]
def _save_audio_history(self):
self.AUDIO_HISTORY_PATH.parent.mkdir(parents=True, exist_ok=True)
with open(self.AUDIO_HISTORY_PATH, "w", encoding="utf-8") as file:
json.dump(self.audio_history, file, indent=2)
def _format_history_entry(self, entry):
source = "Preview" if entry["source"] == "preview" else "Export"
return (
f'{entry["generated_at"]} | {source} | {entry["voice"]} | '
f'{entry["filename"]} | {entry["output_path"]}'
)
def _refresh_history_panel(self):
self.view.historyList.clear()
if not self.audio_history:
self.view.historyList.addItem(
"No generated audio yet. Preview or export speech to populate history."
)
return
for entry in self.audio_history:
item = QListWidgetItem(self._format_history_entry(entry))
item.setToolTip(
"Double-click to play. Right-click for more history actions."
)
item.setData(Qt.ItemDataRole.UserRole, entry)
self.view.historyList.addItem(item)
def toggle_recent_audio(self):
should_expand = self.view.historyList.isHidden()
self.view.historyList.setVisible(should_expand)
if should_expand:
self.view.historyToggleButton.setText("-")
self.view.historyToggleButton.setToolTip("Collapse Recent Audio")
self.view.historyGroup.setMaximumHeight(170)
self.view.historyGroup.setMinimumHeight(48)
self.view.statusbar.showMessage("Recent audio expanded.")
logger.info("Expanded recent audio panel.")
return
self.view.historyToggleButton.setText("+")
self.view.historyToggleButton.setToolTip("Expand Recent Audio")
self.view.historyGroup.setMaximumHeight(48)
self.view.historyGroup.setMinimumHeight(48)
self.view.statusbar.showMessage("Recent audio collapsed.")
logger.info("Collapsed recent audio panel.")
def _history_settings_snapshot(self):
return {
field_name: getattr(self.settings, field_name)
for field_name in self.HISTORY_SETTINGS_FIELDS
if hasattr(self.settings, field_name)
}
def _record_audio_history(self, file_path, source, source_text=None):
audio_path = Path(file_path)
if source_text is None and hasattr(self.view, "textEdit"):
source_text = self._current_editor_text()
entry = {
"filename": audio_path.name,
"output_path": str(audio_path.resolve()),
"voice": self.settings.voice,
"generated_at": datetime.now().strftime("%Y%m%d%H%M%S"),
"source": source,
"source_text": source_text or "",
"settings": self._history_settings_snapshot(),
}
self.audio_history = [
item
for item in self.audio_history
if not (
item.get("output_path") == entry["output_path"]
and item.get("source") == entry["source"]
)
]
self.audio_history.insert(0, entry)
self.audio_history = self.audio_history[: self.MAX_HISTORY_ITEMS]
self._save_audio_history()
self._refresh_history_panel()
logger.info("Recorded {} audio history entry for {}", source, file_path)
def _selected_history_entry(self):
current_item = self.view.historyList.currentItem()
if current_item is not None:
entry = current_item.data(Qt.ItemDataRole.UserRole)
if isinstance(entry, dict):
return entry
current_row = self.view.historyList.currentRow()
if 0 <= current_row < len(self.audio_history):
return self.audio_history[current_row]
return None
def show_history_context_menu(self, position):
entry = self._selected_history_entry()
if not entry:
return
menu = QMenu(self.view)
play_action = menu.addAction("Play Audio")
open_folder_action = menu.addAction("Open Containing Folder")
copy_path_action = menu.addAction("Copy Audio Path")
restore_action = menu.addAction("Restore Text && Settings")
selected_action = menu.exec(self.view.historyList.mapToGlobal(position))
if selected_action == play_action:
self.play_selected_history_audio()
elif selected_action == open_folder_action:
self.open_selected_history_folder()
elif selected_action == copy_path_action:
self.copy_selected_history_path()
elif selected_action == restore_action:
self.restore_selected_history_context()
def play_selected_history_audio(self, *_args):
entry = self._selected_history_entry()
if not entry:
self.view.statusbar.showMessage("Select a history item first.")
return
audio_path = Path(entry.get("output_path", ""))
if not audio_path.exists():
QMessageBox.warning(
self.view,
"Audio Missing",
f"The saved audio file could not be found:\n\n{audio_path}",
)
self.view.statusbar.showMessage("History audio file is missing.")
return
self.latest_audio_path = str(audio_path)
if self.media_player is None or self.audio_output is None:
QMessageBox.information(
self.view,
"Playback Unavailable",
"Multimedia playback is unavailable in this environment.",
)
self.view.statusbar.showMessage(f"Selected history audio: {audio_path}")
return
self.playing_history_audio_path = str(audio_path)
self.media_player.setSource(QUrl.fromLocalFile(str(audio_path)))
self.media_player.play()
self._refresh_action_states()
self.view.statusbar.showMessage(f"Playing history audio: {audio_path.name}")
logger.info("Playing history audio from {}", audio_path)
def open_selected_history_folder(self):
entry = self._selected_history_entry()
if not entry:
self.view.statusbar.showMessage("Select a history item first.")
return
audio_path = Path(entry.get("output_path", ""))
folder_path = audio_path.parent
if not folder_path.exists():
QMessageBox.warning(
self.view,
"Folder Missing",
f"The containing folder could not be found:\n\n{folder_path}",
)
self.view.statusbar.showMessage("History folder is missing.")
return
QDesktopServices.openUrl(QUrl.fromLocalFile(str(folder_path)))
self.view.statusbar.showMessage(f"Opened folder: {folder_path}")
logger.info("Opened history audio folder {}", folder_path)
def copy_selected_history_path(self):
entry = self._selected_history_entry()
if not entry:
self.view.statusbar.showMessage("Select a history item first.")
return
audio_path = entry.get("output_path", "")
QApplication.clipboard().setText(audio_path)
self.view.statusbar.showMessage("Copied history audio path.")
def restore_selected_history_context(self):
entry = self._selected_history_entry()
if not entry:
self.view.statusbar.showMessage("Select a history item first.")
return
source_text = entry.get("source_text", "")
settings_snapshot = entry.get("settings") or {}
if not source_text and not settings_snapshot:
QMessageBox.information(
self.view,
"No History Context",
"This history item does not include reusable text or settings.",
)
self.view.statusbar.showMessage("No reusable history context available.")
return
for field_name in self.HISTORY_SETTINGS_FIELDS:
if field_name in settings_snapshot and hasattr(self.settings, field_name):
setattr(self.settings, field_name, settings_snapshot[field_name])
if source_text:
self.view.textEdit.setPlainText(source_text)
self.settings.save(self.SETTINGS_PATH)
self.tts_processor = None
self._refresh_ui_state()
self.update_ssml_preview()
self.view.statusbar.showMessage("Restored history text and settings.")
logger.info("Restored text/settings from audio history entry.")
def _provider_display_name(self):
provider_name = getattr(self.settings, "tts_provider", "azure")
return get_provider_display_name(provider_name)
def _resolve_tts_provider_config(self):
try:
return resolve_tts_provider_config(self.settings, ".env")
except Exception as error:
logger.warning("TTS provider config unavailable: {}", error)
return None
def _ensure_tts_processor(self):
provider_config = self._resolve_tts_provider_config()
if provider_config is None:
return None
if self.tts_processor is None:
self.tts_processor = TTSProcessor(provider_config=provider_config)
return self.tts_processor
def _build_ssml(self, text):
return build_ssml_document(text, self.settings, self.cleaner)
def _provider_request_metadata(self):
return build_provider_metadata(self.settings)
def _combine_document_rows(self, rows, content_mode="prefer_secondary"):
chunks = []
for row in rows:
primary_text = (row.get("primary_text") or "").strip()
secondary_text = (row.get("secondary_text") or "").strip()
if content_mode == "secondary_only":
resolved_text = secondary_text
elif content_mode == "primary_only":
resolved_text = primary_text
elif content_mode == "combine":
resolved_parts = [part for part in (primary_text, secondary_text) if part]
resolved_text = "\n\n".join(resolved_parts)
else:
resolved_text = secondary_text or primary_text
if resolved_text:
chunks.append(resolved_text)
return "\n\n".join(chunks)
def update_ssml_preview(self):
text = self._current_editor_text()
if not text:
self.view.ssmlPreview.clear()
self._refresh_action_states()
self.view.statusbar.showMessage("Enter text to preview SSML.")
return
provider_profile = get_provider_profile(
getattr(self.settings, "tts_provider", "azure")
)
if not provider_profile.supports_ssml:
self.view.ssmlPreview.setPlainText(
(
f"{self._provider_display_name()} does not expose an SSML preview. "
"This provider sends cleaned text and provider-specific metadata directly to synthesis."
)
)
self._refresh_action_states()
self.view.statusbar.showMessage(
f"{self._provider_display_name()} does not use the SSML preview pane."
)
return
self.view.ssmlPreview.setPlainText(self._build_ssml(text))
self._refresh_action_states()
self.view.statusbar.showMessage("SSML preview updated.")
logger.info("SSML preview updated.")
def clean_text(self):
text = self._current_editor_text()
if not text:
QMessageBox.information(
self.view,
"No Text",
"Paste or type text before cleaning it.",
)
return
cleaned = self.cleaner.clean_all(text)
self.view.textEdit.setPlainText(cleaned)
self.view.statusbar.showMessage("Text cleaned for speech synthesis.")
logger.info("Editor text cleaned for synthesis.")
def generate_audio_bytes(self):
text = self._current_editor_text()
if not text:
QMessageBox.information(
self.view,
"No Text",
"Paste or type text before generating audio.",
)
return None
return self._synthesize_text(text)
def _synthesize_text(self, text):
tts_processor = self._ensure_tts_processor()
if tts_processor is None:
provider_name = self._provider_display_name()
QMessageBox.warning(
self.view,
f"{provider_name} Setup Required",
(
f"The application could not find valid {provider_name} credentials.\n\n"
"Open Tools > Settings, enter the configured provider credentials, "
"and click Apply, or create a valid .env file."
),
)
self.view.statusbar.showMessage(
f"{provider_name} credentials are required before generating speech."
)
return None
try:
provider_input, use_ssml = build_provider_input(
text,
self.settings,
tts_processor.get_capabilities(),
self.cleaner,
)
return tts_processor.text_to_speech(
provider_input,
use_ssml=use_ssml,
voice=self.settings.voice,
metadata=self._provider_request_metadata(),
)
except Exception as error:
logger.exception("Speech generation failed: {}", error)
QMessageBox.critical(
self.view,
"Generation Error",
f"Unable to synthesize speech.\n\n{error}",
)
self.view.statusbar.showMessage("Speech generation failed.")
return None
def generate_and_play_audio(self):
audio_data = self.generate_audio_bytes()
if audio_data is None:
return
self._cleanup_preview_audio()
with tempfile.NamedTemporaryFile(
delete=False,
suffix=".mp3",
) as temp_file:
temp_file.write(audio_data)
self.preview_audio_path = temp_file.name
self.latest_audio_path = temp_file.name
self._record_audio_history(self.preview_audio_path, "preview")
self._refresh_action_states()
if self.media_player is None or self.audio_output is None:
QMessageBox.information(
self.view,
"Playback Unavailable",
"Audio was generated, but multimedia playback is unavailable in this environment.",
)
self.view.statusbar.showMessage(
f"Audio generated at {self.latest_audio_path}"
)
logger.info(
"Generated preview audio without playback support: {}",
self.latest_audio_path,
)
return
self.media_player.setSource(QUrl.fromLocalFile(self.preview_audio_path))
self.playing_history_audio_path = None
self.media_player.play()
self.view.statusbar.showMessage("Playing generated audio.")
logger.info("Playing generated audio from {}", self.preview_audio_path)
def stop_audio(self):
if self.media_player is not None:
self.media_player.stop()
self.playing_history_audio_path = None
self._refresh_action_states()
self.view.statusbar.showMessage("Playback stopped.")
logger.info("Playback stopped.")
def export_audio_file(self):
audio_data = self.generate_audio_bytes()
if audio_data is None:
return
output_dir = Path(self.settings.output_dir)
output_dir.mkdir(parents=True, exist_ok=True)
file_path, _ = QFileDialog.getSaveFileName(
self.view,
"Save Audio File",
str(output_dir / "speech_output.mp3"),
"MP3 Files (*.mp3)",
)
if not file_path:
self.view.statusbar.showMessage("Audio export canceled.")
return
with open(file_path, "wb") as file:
file.write(audio_data)
self.latest_audio_path = file_path
self._record_audio_history(file_path, "export")
self.view.statusbar.showMessage(f"Saved audio to {file_path}")
logger.info("Saved audio export to {}", file_path)
def batch_export_imported_rows(self, rows):
if self.batch_export_active:
QMessageBox.information(
self.view,
"Batch Export Running",
"A batch export is already running. Wait for it to finish before starting another one.",
)
return
if not rows:
QMessageBox.information(
self.view,
"Nothing To Export",
"Select one or more imported document rows before batch exporting.",
)
return
provider_config = self._resolve_tts_provider_config()
if provider_config is None:
provider_name = self._provider_display_name()
QMessageBox.warning(
self.view,
f"{provider_name} Setup Required",
(
f"The application could not find valid {provider_name} credentials.\n\n"
"Open Tools > Settings, enter the configured provider credentials, "
"and click Apply, or create a valid .env file."
),
)
self.view.statusbar.showMessage(
f"{provider_name} credentials are required before batch export."
)
return
output_dir = Path(self.settings.output_dir)
output_dir.mkdir(parents=True, exist_ok=True)
selected_dir = QFileDialog.getExistingDirectory(
self.view,
"Choose Batch Export Folder",
str(output_dir),
)
if not selected_dir:
self.view.statusbar.showMessage("Batch export canceled.")
return
self.batch_export_active = True
self._refresh_action_states()
self.view.statusbar.showMessage("Batch export started in the background.")
self.batch_export_thread = QThread(self.view)
self.batch_export_worker = BatchExportWorker(
rows=rows,
output_dir=selected_dir,
settings=self.settings,
provider_config=provider_config,
)
self.batch_export_worker.moveToThread(self.batch_export_thread)
self.batch_export_thread.started.connect(self.batch_export_worker.run)
self.batch_export_worker.progress.connect(self._handle_batch_export_progress)
self.batch_export_worker.finished.connect(self._handle_batch_export_finished)
self.batch_export_worker.failed.connect(self._handle_batch_export_failed)
self.batch_export_worker.cancelled.connect(self._handle_batch_export_cancelled)
self.batch_export_worker.finished.connect(self.batch_export_thread.quit)
self.batch_export_worker.failed.connect(self.batch_export_thread.quit)
self.batch_export_worker.cancelled.connect(self.batch_export_thread.quit)
self.batch_export_worker.finished.connect(self.batch_export_worker.deleteLater)
self.batch_export_worker.failed.connect(self.batch_export_worker.deleteLater)
self.batch_export_worker.cancelled.connect(
self.batch_export_worker.deleteLater
)
self.batch_export_thread.finished.connect(self.batch_export_thread.deleteLater)
self.batch_export_thread.finished.connect(self._clear_batch_export_worker)
self.batch_export_thread.start()
logger.info("Started background batch export to {}", selected_dir)
def _handle_batch_export_progress(self, completed, total, file_path):
self.latest_audio_path = file_path
self.view.statusbar.showMessage(
f"Batch export progress: {completed}/{total} files generated."
)
def _handle_batch_export_finished(self, exported_files):
exported_paths = [Path(file_path) for file_path in exported_files]
self.batch_export_active = False
if not exported_paths:
QMessageBox.information(
self.view,
"No Content",
"The selected rows did not contain exportable content.",
)
self.view.statusbar.showMessage("Batch export finished with no content.")
return
for file_path in exported_paths:
self.latest_audio_path = str(file_path)
self._record_audio_history(file_path, "export")
selected_path = exported_paths[0].parent
self.view.statusbar.showMessage(
f"Batch exported {len(exported_paths)} audio files to {selected_path}"
)
QMessageBox.information(
self.view,
"Batch Export Complete",
(
f"Created {len(exported_paths)} audio files in:\n\n"
f"{selected_path}"
),
)
logger.info(
"Batch exported {} document audio files to {}",
len(exported_paths),
selected_path,
)
def _handle_batch_export_failed(self, message, exported_files):
self.batch_export_active = False
exported_paths = [Path(file_path) for file_path in exported_files]
for file_path in exported_paths:
self.latest_audio_path = str(file_path)
self._record_audio_history(file_path, "export")
if exported_paths:
self.view.statusbar.showMessage(
f"Batch export stopped after {len(exported_paths)} files."
)
else:
self.view.statusbar.showMessage("Batch export failed.")
QMessageBox.critical(
self.view,
"Batch Export Error",
f"Unable to finish batch export.\n\n{message}",
)
def _handle_batch_export_cancelled(self, exported_files):
self.batch_export_active = False
exported_paths = [Path(file_path) for file_path in exported_files]
for file_path in exported_paths:
self.latest_audio_path = str(file_path)
self._record_audio_history(file_path, "export")
self.view.statusbar.showMessage(
f"Batch export canceled after {len(exported_paths)} completed file(s)."
)
QMessageBox.information(
self.view,
"Batch Export Canceled",
f"Created {len(exported_paths)} audio file(s) before cancellation.",
)
logger.info(
"Batch export canceled after {} completed files.",
len(exported_paths),
)
def _clear_batch_export_worker(self):
self.batch_export_thread = None
self.batch_export_worker = None
self.batch_export_active = False
self._refresh_action_states()
def cancel_background_work(self):
cancel_requested = False
if self.batch_export_worker is not None:
self.batch_export_worker.request_cancel()
cancel_requested = True
if self.document_parse_worker is not None:
self.document_parse_worker.request_cancel()
cancel_requested = True
if not cancel_requested:
self.view.statusbar.showMessage("No background task is running.")
self._refresh_action_states()
You can’t perform that action at this time.