update bugs in bulk production

src/anki_hsk_creator/__about__.py

@@ -3,4 +3,4 @@
 # SPDX-FileCopyrightText: 2026-present Wolfang Torres <wolfang.torres@gmail.com>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
-__version__ = "0.2.1"
+__version__ = "0.2.3"

src/anki_hsk_creator/__main__.py

@@ -15,7 +15,7 @@ from .api import (
     select_file,
     select_folder,
 )
-from .constants import DICTATION_TYPE, DICT_TYPE, LANGUAGES, PHRASES_TYPE
+from .constants import DICTATION_TYPE, DICT_TYPE, INPUT, LANGUAGES, PHRASES_TYPE
 from .utility import ProcessFile, ProcessFolder
 
 
@@ -50,7 +50,7 @@ def cli_select_files() -> ProcessFile:
     return input_file
 
 
-def cli_select_folder() -> ProcessFile:
+def cli_select_folder() -> ProcessFolder:
     """Loops until it finds a valid input_folder"""
     print("Select data folder:")
     in_folder = None
@@ -138,10 +138,15 @@ def main():
                 print(f"processing file {input_file} with language {language_id}")
                 process_a_dictation_file(input_file, language_id)
         elif option == "f":
+            for language_id in LANGUAGES.AvailableLanguages:
                 in_folder = cli_select_folder()
-            language_id = cli_select_language()
                 print(f"Selected: {in_folder} with language {language_id}")
-            folder_proccess(in_folder, language_id=language_id)
+                for dirpath, dirnames, filenames in tuple(
+                    in_folder.absolute_input_folder.walk()
+                )[1:]:
+                    if not dirnames and filenames:
+                        folder = select_folder(dirpath.relative_to(INPUT))
+                        folder_proccess(folder, language_id=language_id)
 
 
 if __name__ == "__main__":

src/anki_hsk_creator/anki_generation.py

@@ -12,8 +12,8 @@ from genanki import Deck, Model, Note, Package
 from pinyin_tone_converter.pinyin_tone_converter import PinyinToneConverter
 
 # Local
+from .constants import DICTATION_TYPE, DICT_TYPE, PHRASES_TYPE
 from .utility import DictionaryResult, ProcessFile, ProcessFolder, TranslationResult
-from .constants import DICT_TYPE, DICTATION_TYPE, PHRASES_TYPE
 
 # Constants
 
@@ -262,7 +262,7 @@ def output_anki_package(
                     fields=[
                         result.translated,
                         result.line,
-                        f"[sound:{result.audio_path}]",
+                        f"[sound:{result.audio_path.name}]",
                     ],
                 )
                 deck.add_note(note)
@@ -277,7 +277,7 @@ def output_anki_package(
                         PinyinToneConverter().convert_text(result.pinyin),
                         result.simplified,
                         result.traditional,
-                        f"[sound:{result.audio_path}]",
+                        f"[sound:{result.audio_path.name}]",
                     ],
                 )
                 deck.add_note(note)
@@ -289,7 +289,7 @@ def output_anki_package(
                     fields=[
                         result.translated,
                         result.line,
-                        f"[sound:{result.audio_path}]",
+                        f"[sound:{result.audio_path.name}]",
                     ],
                 )
                 deck.add_note(note)

src/anki_hsk_creator/api.py

@@ -11,8 +11,8 @@ from . import DATA_FOLDER
 from .anki_generation import (
     output_anki_dictation,
     output_anki_dictionary,
-    output_anki_phrase,
     output_anki_package,
+    output_anki_phrase,
 )
 from .constants import (
     DICTATION_TYPE,

src/anki_hsk_creator/proccessor.py

@@ -27,7 +27,11 @@ def dictation_process(
     results = []
     for n, line in enumerate(text_lines):
         audio_line = line.strip()
-        audio_path = process_file.resources / f"N{n:03n}.wav"
+        posible_name = tuple(process_file.resources.glob(f"N{n:03n}-*.wav"))
+        if posible_name:
+            audio_path = posible_name[0]
+        else:
+            audio_path = process_file.resources / f"N{n:03n}-{uuid.uuid1()}.wav"
         if not audio_path.exists():
             wavs, sr = TTS.generate(f"{audio_line}。")
             sf.write(audio_path, wavs[0], sr)
@@ -47,7 +51,11 @@ def translator_process(
     results = []
     for n, line in enumerate(text_lines):
         audio_line = line.strip()
-        audio_path = process_file.resources / f"N{n:03n}.wav"
+        posible_name = tuple(process_file.resources.glob(f"N{n:03n}-*.wav"))
+        if posible_name:
+            audio_path = posible_name[0]
+        else:
+            audio_path = process_file.resources / f"N{n:03n}-{uuid.uuid1()}.wav"
         if not audio_path.exists():
             wavs, sr = TTS.generate(f"{audio_line}。")
             sf.write(audio_path, wavs[0], sr)

src/anki_hsk_creator/utility.py

@@ -196,6 +196,7 @@ class TTS:
         print(f"finish to generate {text}")
         return audio
 
+
 # Clases