diff --git "a/mod_\346\250\231\351\237\263.py" "b/mod_\346\250\231\351\237\263.py" index 4079391..2f43871 100644 --- "a/mod_\346\250\231\351\237\263.py" +++ "b/mod_\346\250\231\351\237\263.py" @@ -844,3 +844,35 @@ def han_ji_piau_im_tng_huan(self, piau_im, piau_im_huat, siann_bu, un_bu, tiau_h # '韻母': zu_im_un_bu, # '聲調': zu_im_siann_tiau # } + +# # ========================================================== +# # 注音法設定和共用變數 +# # ========================================================== +# zu_im_huat_list = { +# "SNI": ["fifteen_yin", "rt", "十五音切語"], +# "TPS": ["Piau_Im", "rt", "方音符號注音"], +# "POJ": ["pin_yin", "rt", "白話字拼音"], +# "TL": ["pin_yin", "rt", "台羅拼音"], +# "BP": ["pin_yin", "rt", "閩拼標音"], +# "TLPA_Plus": ["pin_yin", "rt", "台羅改良式"], +# "DBL": ["Siang_Pai", "rtc", "雙排注音"], +# } + + +# def choose_piau_im_method(piau_im, zu_im_huat, siann_bu, un_bu, tiau_ho): +# """選擇並執行對應的注音方法""" +# if zu_im_huat == "十五音": +# return piau_im.SNI_piau_im(siann_bu, un_bu, tiau_ho) +# elif zu_im_huat == "白話字": +# return piau_im.POJ_piau_im(siann_bu, un_bu, tiau_ho) +# elif zu_im_huat == "台羅拼音": +# return piau_im.TL_piau_im(siann_bu, un_bu, tiau_ho) +# elif zu_im_huat == "閩拼方案": +# return piau_im.BP_piau_im(siann_bu, un_bu, tiau_ho) +# elif zu_im_huat == "方音符號": +# return piau_im.TPS_piau_im(siann_bu, un_bu, tiau_ho) +# elif zu_im_huat == "台語音標": +# siann = piau_im.Siann_Bu_Dict[siann_bu]["台語音標"] or "" +# un = piau_im.Un_Bu_Dict[un_bu]["台語音標"] +# return f"{siann}{un}{tiau_ho}" +# return "" diff --git "a/output7/\343\200\220\346\262\263\346\264\233\346\226\207\350\256\200\346\263\250\351\237\263\343\200\221\343\200\212\350\210\254\350\213\245\346\263\242\347\276\205\350\234\234\345\244\232\345\277\203\347\266\223\343\200\213.xlsx" "b/output7/\343\200\220\346\262\263\346\264\233\346\226\207\350\256\200\346\263\250\351\237\263\343\200\221\343\200\212\350\210\254\350\213\245\346\263\242\347\276\205\350\234\234\345\244\232\345\277\203\347\266\223\343\200\213.xlsx" index 6fe3b44..54852e8 100644 Binary files "a/output7/\343\200\220\346\262\263\346\264\233\346\226\207\350\256\200\346\263\250\351\237\263\343\200\221\343\200\212\350\210\254\350\213\245\346\263\242\347\276\205\350\234\234\345\244\232\345\277\203\347\266\223\343\200\213.xlsx" and "b/output7/\343\200\220\346\262\263\346\264\233\346\226\207\350\256\200\346\263\250\351\237\263\343\200\221\343\200\212\350\210\254\350\213\245\346\263\242\347\276\205\350\234\234\345\244\232\345\277\203\347\266\223\343\200\213.xlsx" differ diff --git a/p702_Ca_Han_Ji_Thak_Im.py b/p702_Ca_Han_Ji_Thak_Im.py index bedd7dd..dd850b6 100644 --- a/p702_Ca_Han_Ji_Thak_Im.py +++ b/p702_Ca_Han_Ji_Thak_Im.py @@ -13,40 +13,9 @@ from mod_標音 import PiauIm from p740_Phua_Im_Ji import PhuaImJi -# ========================================================== -# 注音法設定和共用變數 -# ========================================================== -zu_im_huat_list = { - "SNI": ["fifteen_yin", "rt", "十五音切語"], - "TPS": ["Piau_Im", "rt", "方音符號注音"], - "POJ": ["pin_yin", "rt", "白話字拼音"], - "TL": ["pin_yin", "rt", "台羅拼音"], - "BP": ["pin_yin", "rt", "閩拼標音"], - "TLPA_Plus": ["pin_yin", "rt", "台羅改良式"], - "DBL": ["Siang_Pai", "rtc", "雙排注音"], -} - - -def choose_piau_im_method(piau_im, zu_im_huat, siann_bu, un_bu, tiau_ho): - """選擇並執行對應的注音方法""" - if zu_im_huat == "十五音": - return piau_im.SNI_piau_im(siann_bu, un_bu, tiau_ho) - elif zu_im_huat == "白話字": - return piau_im.POJ_piau_im(siann_bu, un_bu, tiau_ho) - elif zu_im_huat == "台羅拼音": - return piau_im.TL_piau_im(siann_bu, un_bu, tiau_ho) - elif zu_im_huat == "閩拼方案": - return piau_im.BP_piau_im(siann_bu, un_bu, tiau_ho) - elif zu_im_huat == "方音符號": - return piau_im.TPS_piau_im(siann_bu, un_bu, tiau_ho) - elif zu_im_huat == "台語音標": - siann = piau_im.Siann_Bu_Dict[siann_bu]["台語音標"] or "" - un = piau_im.Un_Bu_Dict[un_bu]["台語音標"] - return f"{siann}{un}{tiau_ho}" - return "" - -def cu_siann_un_tiau(result, han_ji_khoo, piau_im, piau_im_huat): - """查詢【漢字庫】取得之【查找結果】，將之切分：聲、韻、調""" + +def za_ji_kiat_ko_cut_piau_im(result, han_ji_khoo, piau_im, piau_im_huat): + """查字結果出標音：查詢【漢字庫】取得之【查找結果】，將之切分：聲、韻、調""" if han_ji_khoo == "河洛話": #----------------------------------------------------------------- # 【白話音】：依《河洛話漢字庫》標注【台語音標】和【方音符號】 @@ -66,10 +35,9 @@ def cu_siann_un_tiau(result, han_ji_khoo, piau_im, piau_im_huat): if siann_bu == "" or siann_bu == None: siann_bu = "ø" - # 將【聲母】、【韻母】、【聲調】，合併成【台語音標】 - # tai_gi_im_piau = siann_bu + un_bu + tiau_ho - tai_gi_im_piau = ''.join([siann_bu, un_bu, tiau_ho]) + # tai_gi_im_piau = ''.join([siann_bu, un_bu, tiau_ho]) + tai_gi_im_piau = siann_bu + un_bu + tiau_ho # 標音法為：【十五音】或【雅俗通】，且【聲母】為空值，則將【聲母】設為【ø】 if (piau_im_huat == "十五音" or piau_im_huat == "雅俗通") and (siann_bu == "" or siann_bu == None): @@ -83,7 +51,9 @@ def cu_siann_un_tiau(result, han_ji_khoo, piau_im, piau_im_huat): ) return tai_gi_im_piau, han_ji_piau_im + def ca_han_ji_thak_im(wb, sheet_name='漢字注音', cell='V3', hue_im="白話音", han_ji_khoo="河洛話", db_name='Ho_Lok_Ue.db', module_name='mod_河洛話', function_name='han_ji_ca_piau_im'): + """查漢字讀音：依【漢字】查找【台語音標】，並依指定之【標音方法】輸出【漢字標音】""" # 初始化 PiauIm 類別，産生標音物件 piau_im = PiauIm(han_ji_khoo=han_ji_khoo) piau_im_huat = wb.names['標音方法'].refers_to_range.value @@ -152,11 +122,15 @@ def ca_han_ji_thak_im(wb, sheet_name='漢字注音', cell='V3', hue_im="白話 print(f"({row}, {col_name}) = {msg}") index += 1 continue - else: - han_ji = cell_value + # 自儲存格取出【漢字】 + han_ji = cell_value + han_ji_u_piau_im = False + + # 依據【人工標音】欄是否有輸入，決定【漢字標音】之處理方式 manual_input = sheet.range((row-2, col)).value - if manual_input: # 若【手動輸入】的欄位有輸入 + + if manual_input: # 若有人工輸入之處理作業 if '〔' in manual_input and '〕' in manual_input: # 將人工輸入的〔台語音標〕轉換成【方音符號】 im_piau = manual_input.split('〔')[1].split('〕')[0] @@ -168,6 +142,7 @@ def ca_han_ji_thak_im(wb, sheet_name='漢字注音', cell='V3', hue_im="白話 piau_im_huat=piau_im_huat, tai_gi_im_piau=tai_gi_im_piau ) + han_ji_u_piau_im = True elif '【' in manual_input and '】' in manual_input: # 將人工輸入的【方音符號】轉換成【台語音標】 han_ji_piau_im = manual_input.split('【')[1].split('】')[0] @@ -179,30 +154,28 @@ def ca_han_ji_thak_im(wb, sheet_name='漢字注音', cell='V3', hue_im="白話 tiau=tiau, cursor=cursor, )['台語音標'] + han_ji_u_piau_im = True else: - # 將人工輸入，沒有以[中括號]標示的【台語音標】轉換成【方音符號】 - im_piau = manual_input - siann, un, tiau = split_tai_gi_im_piau(im_piau) - tai_gi_im_piau = ''.join([siann, un, tiau]) - # 依使用者指定之【標音方法】，將【台語音標】轉換成其所需之【漢字標音】 - han_ji_piau_im = tlpa_tng_han_ji_piau_im( - piau_im=piau_im, - piau_im_huat=piau_im_huat, - tai_gi_im_piau=tai_gi_im_piau + # 將人工輸入的【台語音標】，解構為【聲母】、【韻母】、【聲調】 + tai_gi_im_piau = manual_input + siann, un, tiau = split_tai_gi_im_piau(tai_gi_im_piau) + # 依指定之【標音方法】，將【台語音標】轉換成其所需之【漢字標音】 + han_ji_piau_im = tng_uann_han_ji_piau_im( + piau_im, + piau_im_huat, + siann, + un, + tiau ) + han_ji_u_piau_im = True # 將人工輸入的【台語音標】置入【破音字庫】Dict phua_im_ji.ka_phua_im_ji(han_ji, tai_gi_im_piau) - - sheet.range((row - 1, col)).value = tai_gi_im_piau - sheet.range((row + 1, col)).value = han_ji_piau_im - print(f"({row}, {col_name}) = {han_ji} [{tai_gi_im_piau}] 【{han_ji_piau_im}】") - else: - """無人工輸入則自動查找""" + else: # 無人工輸入，則自【漢字庫】查找作業 # 查找【破音字庫】，確認是否有此漢字 - han_ji_u_piau_im = False found = phua_im_ji.ca_phua_im_ji(han_ji) - if found: # 若【破音字庫】有此漢字 + # 若【破音字庫】有此漢字 + if found: siann_bu, un_bu, tiau_ho = split_tai_gi_im_piau(found) tai_gi_im_piau = siann_bu + un_bu + tiau_ho han_ji_piau_im = tng_uann_han_ji_piau_im( @@ -213,26 +186,30 @@ def ca_han_ji_thak_im(wb, sheet_name='漢字注音', cell='V3', hue_im="白話 tiau_ho ) han_ji_u_piau_im = True - else: # 若【破音字庫】無此漢字，則在資料庫中查找 + sheet.range((row, col)).font.color = (255, 0, 0) # 將文字顏色設為【紅色】 + sheet.range((row, col)).color = (255, 255, 0) # 將底色設為【黄色】 + print(f"漢字：【{han_ji}】之注音【{tai_gi_im_piau}】取自【人工注音字典】。") + # 若【破音字庫】無此漢字，則在資料庫中查找 + else: result = han_ji_ca_piau_im(cursor=cursor, han_ji=han_ji, hue_im=hue_im) if not result: - msg = f"【{cell_value}】查無此字！" + msg = f"【{han_ji}】查無此字！" else: - tai_gi_im_piau, han_ji_piau_im = cu_siann_un_tiau( + # 依【漢字庫】查找結果，輸出【台語音標】和【漢字標音】 + tai_gi_im_piau, han_ji_piau_im = za_ji_kiat_ko_cut_piau_im( result=result, han_ji_khoo=han_ji_khoo, piau_im=piau_im, piau_im_huat=piau_im_huat ) - han_ji_u_piau_im = True + han_ji_u_piau_im = True if han_ji_u_piau_im: sheet.range((row - 1, col)).value = tai_gi_im_piau sheet.range((row + 1, col)).value = han_ji_piau_im - print(f"({row}, {col_name}) = {han_ji} [{tai_gi_im_piau}] 【{han_ji_piau_im}】") - else: - print(f"({row}, {col_name}) = {msg}") + msg = f"{han_ji}： [{tai_gi_im_piau}] /【{han_ji_piau_im}】" + print(f"({row}, {col_name}) = {msg}") index += 1 row += 4 diff --git a/p740_Phua_Im_Ji.py b/p740_Phua_Im_Ji.py index cf445fa..446eb13 100644 --- a/p740_Phua_Im_Ji.py +++ b/p740_Phua_Im_Ji.py @@ -10,14 +10,14 @@ class PhuaImJi: """ def __init__(self, ji_tian_name="Phua_Im_Ji.json"): - # 破音字典存放漢字與注音 + # 【人工注音字典】存放漢字與注音 self.phua_im_ji_tian = {} self.Ji_Tian_Name = ji_tian_name def ka_phua_im_ji(self, han_ji, piau_im): """ - 將【漢字】與【注音】加入破音字典。 + 將【漢字】與【注音】加入【人工注音字典】。 參數： - han_ji: str，單一漢字。 @@ -26,7 +26,7 @@ def ka_phua_im_ji(self, han_ji, piau_im): if len(han_ji) != 1: raise ValueError("輸入的 char 必須是一個單一漢字。") self.phua_im_ji_tian[han_ji] = piau_im - print(f"已將 {han_ji} 的注音「{piau_im}」加入破音字典。") + print(f"漢字：【{han_ji}】之注音【{piau_im}】已加入【人工注音字典】。") def ca_phua_im_ji(self, han_ji): @@ -37,39 +37,39 @@ def ca_phua_im_ji(self, han_ji): - han_ji: str，單一漢字。 返回： - - str 或 None：若存在於破音字典則返回注音，否則返回 None。 + - str 或 None：若存在於【人工注音字典】則返回注音，否則返回 None。 """ return self.phua_im_ji_tian.get(han_ji, None) def save_to_file(self): """ - 將破音字典以純文字 JSON 格式存入檔案。 + 將【人工注音字典】以純文字 JSON 格式存入檔案。 """ file_path = self.Ji_Tian_Name with open(file_path, 'w', encoding='utf-8') as f: json.dump(self.phua_im_ji_tian, f, ensure_ascii=False, indent=4) - print(f"破音字典已儲存至 {file_path}") + print(f"【人工注音字典】已儲存至 {file_path}") def load_from_file(self): """ - 從 JSON 格式檔案讀取破音字典。 + 從 JSON 格式檔案讀取【人工注音字典】。 """ file_path = self.Ji_Tian_Name with open(file_path, 'r', encoding='utf-8') as f: self.phua_im_ji_tian = json.load(f) - print(f"已從 {file_path} 載入破音字典") + print(f"已從 {file_path} 載入【人工注音字典】") def dump_phua_im_ji_tian(self): """ - 在螢幕上輸出破音字典的內容，以純文字格式顯示。 + 在螢幕上輸出【人工注音字典】的內容，以純文字格式顯示。 """ if not self.phua_im_ji_tian: - print("破音字典為空。") + print("【人工注音字典】為空。") else: - print("破音字典內容如下：") + print("【人工注音字典】內容如下：") print("{") for han_ji, piau_im in self.phua_im_ji_tian.items(): print(f" '{han_ji}': '{piau_im}',") @@ -78,20 +78,20 @@ def dump_phua_im_ji_tian(self): def save_to_bin_file(self, file_path): """ - 將破音字典存入檔案。 + 將【人工注音字典】存入檔案。 """ with open(file_path, 'wb') as f: pickle.dump(self.phua_im_ji_tian, f) - print(f"破音字典已儲存至 {file_path}") + print(f"【人工注音字典】已儲存至 {file_path}") def load_from_bin_file(self, file_path): """ - 從檔案讀取破音字典。 + 從檔案讀取【人工注音字典】。 """ with open(file_path, 'rb') as f: self.phua_im_ji_tian = pickle.load(f) - print(f"已從 {file_path} 載入破音字典") + print(f"已從 {file_path} 載入【人工注音字典】") # 單元測試 @@ -116,7 +116,7 @@ def load_from_bin_file(self, file_path): # 從 JSON 檔案讀取 phua_im_ji.load_from_file() - # 在螢幕上輸出破音字典 + # 在螢幕上輸出【人工注音字典】 phua_im_ji.dump_phua_im_ji_tian() # 查詢注音