rename files and add chat tts

anki-hsk-creator/__main__.py

@@ -18,7 +18,8 @@ INPUT = DATA / "input"
 OUTPUT = DATA / "output"
 CN = "zh"
 EN = "en"
-TEXT_TYPE = "TEXT_TYPE"
+PHRASES_TYPE = ".phrases"
+DICT_TYPE = ".dictionary"
 CSS = """
 .card {
  font-family: arial;
@@ -127,14 +128,21 @@ def create_translator():
 
 def process_files():
     print("Select data file:")
-    files = []
+    in_file = None
-    for n, file in enumerate(INPUT.glob("**/*.txt")):
+    level = INPUT
-        files.append(file)
+    while not in_file:
-        print(f"{n+1} - {file.relative_to(INPUT)}")
+        files = []
-    s = None
+        for n, file in enumerate(level.glob("*")):
-    while not s or not s.isnumeric() or not (1 <= int(s) <= len(files)):
+            files.append(file)
-        s = input(f"Please select the file [1-{len(files)}]: ")
+            print(f"{n+1} - {file.relative_to(INPUT)}")
-    in_file = files[int(s) - 1]
+        s = None
+        while not s or not s.isnumeric() or not (1 <= int(s) <= len(files)):
+            s = input(f"Please select the file [1-{len(files)}]: ")
+        selected = files[int(s) - 1]
+        if selected.is_file():
+            in_file = selected
+        else:
+            level = selected
     relative = in_file.relative_to(INPUT)
     out_file = OUTPUT / relative
     out_file.parent.mkdir(parents=True, exist_ok=True)
@@ -147,25 +155,34 @@ def dictionary_process(dictionary, in_file):
     """Process dictionary files"""
     words_list = in_file.open(encoding="utf8").read().split()
     results = [] 
-    for word in words_list:
+    with in_file.open("w", encoding="utf8") as input_file:
-        if v := dictionary.get(word):
+        for words in words_list:
-            if len(v) > 1:
+            word = words.split()[0]
-                print(f"\nWARNING: {word} has multiple meanings:")
+            pinyin = words.split()[1] if len(words.split()) > 1 else None
-                for n, w in enumerate(v):
+            if v := dictionary.get(word):
-                    print(f"{n+1} - {w}")
+                if len(v) > 1:
-                    for m in w.meanings:
+                    print(f"\nWARNING: {word} has multiple meanings:")
-                        print(f"\t{m}")
+                    if pinyin and pinyin != "ERROR":
-                s = None
+                        ml = filter(lambda x: v.pinyin == pinyin, v)
-                while not s or not s.isnumeric() or not (1 <= int(s) <= len(v)):
+                    else:
-                    s = input(f"Please select the correct word [1-{len(v)}]: ")
+                        ml = v
-                v = v[int(s) - 1]
+                        for n, w in enumerate(ml):
+                            print(f"{n+1} - {w}")
+                            for m in w.meanings:
+                                print(f"\t{m}")
+                    s = None
+                    while not s or not s.isnumeric() or not (1 <= int(s) <= len(v)):
+                        s = input(f"Please select the correct word [1-{len(v)}]: ")
+                    v = v[int(s) - 1]
+                else:
+                    v = v[0]
+                input_file.write(f"{word}\t{v.pinyin}\n")
+                results.append(v)
             else:
-                v = v[0]
+                print("============================================")
-            results.append(v)
+                print(f"===================>ERROR: {word} not found")
-        else:
+                print("============================================")
-            print("============================================")
+                input_file.write(f"{word}\tERROR\n")
-            print(f"===================>ERROR: {word} not found")
-            print("============================================")
     return results
 
 
@@ -231,14 +248,16 @@ def output_anki_text(out_file, results):
 
 def main():
     in_file, out_file, file_type = process_files()
-    if TEXT_TYPE == file_type:
+    if PHRASES_TYPE in in_file.suffixes:
         create_translator()
         results = translator_process(in_file)
         output_anki_text(out_file, results)
-    else:
+    elif DICT_TYPE in in_file.suffixes:
         dictionary = create_cedict()
         results = dictionary_process(dictionary, in_file)
         output_anki_dictionary(out_file, results)
+    else:
+        raise TypeError("Error, filetype not especified!")
 
 
 if __name__ == "__main__":

data/input/HSK1/HSK1-1.dictionary.txt

@@ -1,9 +1,9 @@
 你
 好
-你好
 您
+你好
 您好
-你们
+你们好
-您们
+您们好
 对不起
 没关系

data/input/HSK1/HSK1-1.phrases.txt

@@ -1,4 +1,3 @@
-TEXT_TYPE
 上课
 下课
 想在休息

data/input/HSK1/HSK1-2.phrases.txt

@@ -1,3 +1,2 @@
-TEXT_TYPE
 不谢
 谢谢你

data/input/口语/口语-第10课.phrases.txt

@@ -1,4 +1,3 @@
-TEXT_TYPE
 衣村生活
 新农村
 环境优美

data/input/口语/口语-第9课.phrases.txt

@@ -1,2 +1 @@
-TEXT_TYPE
 周六那场篮球比在，对手很厉害。前半场他们一直赢，后半场我们对才超过他们，领先得并不轻松。

setup.py

@@ -9,5 +9,6 @@ setup(
         "pinyin-tone-converter",
         "genanki",
         "argostranslate",
+        "chattts",
     ],
 )