wolfang/anki-hsk-creator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update bugfixes

Browse Source
This commit is contained in:
Wolfang Torres
2026-06-27 16:29:36 +08:00
parent 7cb0894abd
commit 9437d5ed7a
5 changed files with 93 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/anki_hsk_creator/__about__.py
View File

@@ -3,4 +3,4 @@
# SPDX-FileCopyrightText: 2026-present Wolfang Torres <wolfang.torres@gmail.com>
#
# SPDX-License-Identifier: GPL-3.0-or-later
__version__ = "0.2.0"
__version__ = "0.2.1"

64
src/anki_hsk_creator/anki_generation.py
View File

@@ -13,6 +13,7 @@ from pinyin_tone_converter.pinyin_tone_converter import PinyinToneConverter
# Local
from .utility import DictionaryResult, ProcessFile, ProcessFolder, TranslationResult
from .constants import DICT_TYPE, DICTATION_TYPE, PHRASES_TYPE
# Constants
@@ -241,31 +242,60 @@ def output_anki_phrase(
def output_anki_package(
process_folder: ProcessFolder, results: dict[ProcessFile, list[TranslationResult]]
):
final_file = process_file.output_name.with_suffix(".apkg")
final_file = process_folder.output_name.with_suffix(".apkg")
decks = []
audios = []
for process_file, results in results.items():
deck_name = "::".join(
ProcessFolder.input_folder.parts[:-1] + (ProcessFolder.output_name.stem,)
process_file.input_file.parts[:-1] + (process_file.output_name.stem,)
)
deck = Deck(
random.randrange(1 << 30, 1 << 31),
deck_name,
f"Deck for {final_file.name}, "
f"Deck for {process_file.input_file}, "
"created in https://www.wolfang.info.ve/hskankicreator/",
)
for result in results:
note = Note(
model=DICTATION_MODEL,
fields=[
result.translated,
result.line,
f"[sound:{result.audio_path}]",
],
)
deck.add_note(note)
audios.append(result.audio_path)
if process_file.file_type is DICTATION_TYPE:
for result in results:
note = Note(
model=DICTATION_MODEL,
fields=[
result.translated,
result.line,
f"[sound:{result.audio_path}]",
],
)
deck.add_note(note)
audios.append(result.audio_path)
elif process_file.file_type is DICT_TYPE:
for result in results:
note = Note(
model=HSK_MODEL,
fields=[
# "\n ".join(f"{n+1}. {m}" for n, m in enumerate(result.meanings)),
result.meaning,
PinyinToneConverter().convert_text(result.pinyin),
result.simplified,
result.traditional,
f"[sound:{result.audio_path}]",
],
)
deck.add_note(note)
audios.append(result.audio_path)
elif process_file.file_type is PHRASES_TYPE:
for result in results:
note = Note(
model=PHRASE_MODEL,
fields=[
result.translated,
result.line,
f"[sound:{result.audio_path}]",
],
)
deck.add_note(note)
audios.append(result.audio_path)
decks.append(deck)
package = Package(decks)
package.media_files = audios
package.write_to_file(final_file)
package = Package(decks)
package.media_files = audios
package.write_to_file(final_file)
return final_file

27
src/anki_hsk_creator/api.py
View File

@@ -12,6 +12,7 @@ from .anki_generation import (
output_anki_dictation,
output_anki_dictionary,
output_anki_phrase,
output_anki_package,
)
from .constants import (
DICTATION_TYPE,
@@ -84,7 +85,7 @@ def select_file(file_path: Path) -> ProcessFile:
def select_folder(file_path: Path) -> ProcessFile:
"""Given a relative path from `list_input_files`, return a ProcessFile"""
if (INPUT / file_path).is_dir():
return ProcessFile(file_path)
return ProcessFolder(file_path)
else:
raise ValueError(f"{file_path} is not a folder")
@@ -254,25 +255,27 @@ def folder_proccess(process_folder: ProcessFolder, language_id: str):
TRANS.create_translator(LANGUAGES.CN, language_id)
CCCEDICT.create_cedict(language_id)
results = {}
for file in process_folder.input_files:
if file.file_type is DICT_TYPE:
with file.absolute_input_file.open(
for process_file in process_folder.input_files:
print(f"Proccessing {process_file}")
if process_file.file_type is DICT_TYPE:
with process_file.absolute_input_file.open(
"r", encoding="utf8", newline="\n"
) as file:
words_list = [word.strip() for word in file.readlines() if word]
dictionary_bulk_process(words_list, file)
results[file] = dictionary_process(file)
elif file.file_type is DICTATION_TYPE:
with file.absolute_input_file.open(
dictionary_bulk_process(words_list, process_file)
results[process_file] = dictionary_process(process_file)
elif process_file.file_type is DICTATION_TYPE:
with process_file.absolute_input_file.open(
"r", encoding="utf8", newline="\n"
) as file:
text_lines = [
line.strip() for line in file.read().split("。") if line.strip()
]
results[file] = dictation_process(text_lines, file)
elif file.file_type is PHRASES_TYPE:
with file.absolute_input_file.open(
results[process_file] = dictation_process(text_lines, process_file)
elif process_file.file_type is PHRASES_TYPE:
with process_file.absolute_input_file.open(
"r", encoding="utf8", newline="\n"
) as file:
text_lines = [line.strip() for line in file.readlines() if line.strip()]
results[file] = translator_process(text_lines, file)
results[process_file] = translator_process(text_lines, process_file)
return output_anki_package(process_folder, results)

32
src/anki_hsk_creator/proccessor.py
View File

@@ -14,7 +14,7 @@ from .utility import CCCEDICT, TTS, DictionaryResult, ProcessFile, TranslationRe
# Constants
FIELDNAMES = ["n" "simplified", "traditional", "pinyin", "meaning"]
FIELDNAMES = ["n", "simplified", "traditional", "pinyin", "meaning"]
DIALECT = "excel-tab"
# Results Classes
@@ -80,38 +80,36 @@ def dictionary_bulk_process(words_list: list[str], process_file: ProcessFile):
[
entry
for entry in entries
for meaning in entry.meaning
for meaning in entry.meanings
if hint in meaning
]
if hint
else []
)
pos_entries = pos_meanings or entries
meanings = "\n".join(
f"{i} - {entry.meaning}" for i, entry in enumerate(pos_entries)
)
meanings = []
for entry in pos_entries:
for meaning in entry.meanings:
if hint and hint in meaning:
meanings.append(meaning)
if not meanings:
meanings = [
meaning for entry in pos_entries for meaning in entry.meanings
]
meanings_text = meanings[0]
tsv_writer.writerow(
{
"n": n,
"n": number,
"simplified": entry.simplified,
"traditional": entry.traditional,
"pinyin": entry.pinyin,
"meaning": meanings,
"meaning": meanings_text,
}
)
else:
print("============================================")
print(f"===================>ERROR: {word} not found")
print("============================================")
tsv_writer.writerow(
{
"n": number,
"simplified": word,
"traditional": None,
"pinyin": None,
"meaning": None,
}
)
number += 1
@@ -163,7 +161,7 @@ def dictionary_pre_process(words_list: list[str], process_file: ProcessFile):
print("============================================")
tsv_writer.writerow(
{
"n": n,
"n": number,
"simplified": word,
"traditional": None,
"pinyin": None,

27
src/anki_hsk_creator/utility.py
View File

@@ -161,7 +161,6 @@ class TTS:
DEVICE = None
DEFAULTS = {
"language": "Chinese",
"speaker": "Uncle_Fu",
"instruct": "语速缓慢而审慎，每个音节的语调都拿捏得恰到好处，宛如教授在指导新生。",
"instruct": "Speak in a slow pace and enuntiate every word, as a teacher to a learning student",
}
@@ -189,11 +188,13 @@ class TTS:
@staticmethod
def generate(text: str):
"""Generates a Waw using the defaulst values"""
print(f"starting to generate {text}")
speaker = random.choice(TTS.VOICES)
return TTS.MODEL.generate_custom_voice(
audio = TTS.MODEL.generate_custom_voice(
text=text, **TTS.DEFAULTS, speaker=speaker
)
print(f"finish to generate {text}")
return audio
# Clases
@@ -207,6 +208,7 @@ class ProcessFolder:
def __init__(self, input_folder: Path, language_id: str = None):
self.input_folder = input_folder
self._language_id = language_id
self.absolute_input_folder = INPUT / self.input_folder
# process file type
self.out_folder = OUTPUT / input_folder
self.out_folder.mkdir(parents=True, exist_ok=True)
@@ -214,24 +216,23 @@ class ProcessFolder:
self.resources.mkdir(parents=True, exist_ok=True)
@property
def output_name():
def output_name(self):
"""Posible name for the output file, still missing the filetype"""
if self.language_id is None:
raise ValueError("Not a valid language selected")
return self.out_folder / f"{self.input_file.stem}.{self.language_id}.temp"
@property
def absolute_input_file(self):
"""Absolute input file"""
return INPUT / self.input_file
return self.out_folder / f"{self.input_folder.stem}.{self.language_id}.temp"
@property
def input_files(self):
input_files = []
for file in self.absolute_input_file.glob(f"*.txt"):
for file in self.absolute_input_folder.glob(f"*.txt"):
for file_type in (DICT_TYPE, PHRASES_TYPE, DICTATION_TYPE):
if file_type in file.suffixes:
input_files.append(ProcessFile(file, language_id=self.language_id))
input_files.append(
ProcessFile(
file.relative_to(INPUT), language_id=self.language_id
)
)
return input_files
@property
@@ -339,6 +340,7 @@ class DictionaryResult:
def __init__(
self,
n: str,
language_id: str,
simplified: str,
traditional: str,
@@ -346,6 +348,7 @@ class DictionaryResult:
meaning: str,
audio_path: Path,
):
self.n = n
self.language_id = language_id
self.simplified = simplified
self.traditional = traditional