update to use RE for spliting text

src/anki_hsk_creator/api.py

@@ -4,6 +4,7 @@ Interface for managuing and procesing files
 """
 
 # Standard Library
+import re
 from pathlib import Path
 
 # Local
@@ -234,7 +235,9 @@ def process_a_dictation_file(process_file: ProcessFile, language_id: str) -> Pat
     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()]
+        text = file.read().strip()
+        result = re.split(r"[！？。；]*", text)
+        text_lines = [line.strip() for line in result if line.strip()]
     results = dictation_process(text_lines, process_file)
     return output_anki_dictation(process_file, results)
 
@@ -313,7 +316,7 @@ def folder_proccess(process_folder: ProcessFolder, language_id: str):
                         line.strip() for line in file.readlines() if line.strip()
                     ]
                 results[process_file] = completed_process(text_lines, process_file)
-        except (AttributeError, AssertionError):
+        except AttributeError, AssertionError:
             print(f"Error procesing {process_file} with language {language_id}")
             continue
     return output_anki_package(process_folder, results)

src/anki_hsk_creator/proccessor.py

@@ -110,18 +110,20 @@ def dictionary_bulk_process(words_list: list[str], process_file: ProcessFile):
             entries_en = dictionary_en.get(word)
             entries = dictionary.get(word)
             if entries:
-                all_meanings = [meaning for entry in entries for meaning in entry.meanings]
+                all_meanings = [
+                    meaning for entry in entries for meaning in entry.meanings
+                ]
                 pos_meanings = [
                     meaning
                     for entry, entry_en in zip(entries, entries_en)
-                    for meaning, meaning_en in zip(
-                        entry.meanings, entry_en.meanings
-                    )
+                    for meaning, meaning_en in zip(entry.meanings, entry_en.meanings)
                     if hint and (hint in meaning_en or hint in meaning)
                 ]
                 pos_meanings = pos_meanings or all_meanings
                 if not pos_meanings:
-                    raise ValueError(f"Not menaing found for hint {hint}, {all_meanings}")
+                    raise ValueError(
+                        f"Not menaing found for hint {hint}, {all_meanings}"
+                    )
                 meanings_text = "\n".join(
                     f"{n+1}: {meaning}" for n, meaning in enumerate(pos_meanings)
                 )