From fcdaf2b2a837d7525d922e586ee0310ec4861d14 Mon Sep 17 00:00:00 2001
From: Artem Akymenko <akimenko.artem@gmail.com>
Date: Sat, 18 Jul 2026 09:00:24 +0000
Subject: [PATCH] refactor(domain): extract FakeToken to domain/tokens.py

Shared token stub used by both WebUI and PyQt for languages
without per-word token support.
---
 abogen/domain/tokens.py           | 13 +++++++++++++
 abogen/pyqt/conversion.py         |  9 +--------
 abogen/webui/conversion_runner.py | 13 ++-----------
 3 files changed, 16 insertions(+), 19 deletions(-)
 create mode 100644 abogen/domain/tokens.py

diff --git a/abogen/domain/tokens.py b/abogen/domain/tokens.py
new file mode 100644
index 0000000..5a8c8b2
--- /dev/null
+++ b/abogen/domain/tokens.py
@@ -0,0 +1,13 @@
+"""Shared token stubs for TTS processing."""
+
+from __future__ import annotations
+
+
+class FakeToken:
+    """Minimal token stub for languages without per-word token support."""
+
+    def __init__(self, text: str, start: float, end: float):
+        self.text = text
+        self.start_ts = start
+        self.end_ts = end
+        self.whitespace = ""
diff --git a/abogen/pyqt/conversion.py b/abogen/pyqt/conversion.py
index 3a86005..852e164 100644
--- a/abogen/pyqt/conversion.py
+++ b/abogen/pyqt/conversion.py
@@ -31,6 +31,7 @@ from abogen.domain.output_paths import (
 )
 from abogen.domain.audio_helpers import build_ffmpeg_command, to_float32
 from abogen.domain.audio_sink import AudioSink, open_audio_sink
+from abogen.domain.tokens import FakeToken
 from abogen.domain.audio_buffer import (
     create_silence,
     mix_audio,
@@ -1086,14 +1087,6 @@ class ConversionThread(QThread):
                                 # Fallback for languages without token support (non-English)
                                 # Create a single token representing the entire segment duration
                                 if not tokens_list and result.graphemes:
-
-                                    class FakeToken:
-                                        def __init__(self, text, start, end):
-                                            self.text = text
-                                            self.start_ts = start
-                                            self.end_ts = end
-                                            self.whitespace = ""
-
                                     tokens_list = [
                                         FakeToken(result.graphemes, 0, chunk_dur)
                                     ]
diff --git a/abogen/webui/conversion_runner.py b/abogen/webui/conversion_runner.py
index 4e0a728..2789da9 100644
--- a/abogen/webui/conversion_runner.py
+++ b/abogen/webui/conversion_runner.py
@@ -121,6 +121,7 @@ from abogen.domain.audio_buffer import (
     SAMPLE_RATE,
 )
 from abogen.domain.audio_sink import AudioSink, open_audio_sink
+from abogen.domain.tokens import FakeToken
 
 
 from .service import Job, JobStatus
@@ -132,16 +133,6 @@ SPLIT_PATTERN = r"\n+"  # Kept for backward compatibility; prefer get_split_patt
 SAMPLE_RATE = 24000
 
 
-class _FakeToken:
-    """Minimal token stub for languages without per-word token support."""
-
-    def __init__(self, text: str, start: float, end: float):
-        self.text = text
-        self.start_ts = start
-        self.end_ts = end
-        self.whitespace = ""
-
-
 class _JobCancelled(Exception):
     """Raised internally to abort a conversion when the client cancels."""
 
@@ -543,7 +534,7 @@ def run_conversion_job(job: Job) -> None:
 
                         # Fallback for languages without token support: create a single token
                         if not tokens_list and graphemes:
-                            tokens_list = [_FakeToken(graphemes, 0, duration)]
+                            tokens_list = [FakeToken(graphemes, 0, duration)]
 
                         for tok in tokens_list:
                             accumulated_tokens.append({