add suport for paragraph trsanlations

anki-hsk-creator/__main__.py

@@ -1,14 +1,14 @@
 ## Imports
 from pathlib import Path
+import random
 import csv
 
+## PIP
 from cedict_utils.cedict import CedictParser
 from pinyin_tone_converter.pinyin_tone_converter import PinyinToneConverter
-
+from genanki import Deck, Note, Model, Package
-# from genanki import Deck, Note
+import argostranslate.package
-
+import argostranslate.translate
-# import argostranslate.package
-# import argostranslate.translate
 
 ## Constants
 
@@ -16,40 +16,76 @@ CCCEDICT = Path(__file__).parent / "cedict_ts.u8"
 DATA = Path(__file__).parent.parent / "data"
 INPUT = DATA / "input"
 OUTPUT = DATA / "output"
-CN = "cn"
+CN = "zh"
 EN = "en"
+TEXT_TYPE = "TEXT_TYPE"
+CSS = """
+.card {
+ font-family: arial;
+ font-size: 20px;
+ text-align: center;
+ color: black;
+ background-color: white;
+}
+.simple {
+font-family: Arial;
+font-size: 100px;
+}
+.trad {
+font-family: Arial;
+font-size: 75px;
+}
+"""
 
 ## Classess
 
-## Main
+SIMPLE_MODEL = Model(
+    2076166425,
+    "Simple Model",
+    fields=[
+        {"name": "Question"},
+        {"name": "Answer"},
+    ],
+    templates=[
+        {
+            "name": "Card 1",
+            "qfmt": "{{Question}}",
+            "afmt": '{{FrontSide}}<hr id="answer">{{Answer}}',
+        },
+    ],
+    css=CSS,
+)
 
-# Download and install Argos Translate package
+HSK_MODEL = Model(
-# argostranslate.package.update_package_index()
+    1708536519,
-# available_packages = argostranslate.package.get_available_packages()
+    "HSK Model",
-# package_to_install = next(
+    fields=[
-#     filter(
+        {"name": "English"},
-#         lambda x: x.from_code == CN and x.to_code == EN, available_packages
+        {"name": "Pinyin"},
-#     )
+        {"name": "Simplified"},
-# )
+        {"name": "Traditional"},
-# argostranslate.package.install_from_path(package_to_install.download())
+    ],
+    templates=[
+        {
+            "name": "Card 1",
+            "qfmt": "<strong>{{Pinyin}}</strong><br>{{English}}",
+            "afmt": "{{FrontSide}}<hr id='answer''><div class='simple'>{{Simplified}}</div><br><div class='trad'>{{Traditional}}</div>",
+        },
+        {
+            "name": "Card 2",
+            "qfmt": "<div class='simple'>{{Simplified}}</div><br><div class='trad'>{{Traditional}}</div>",
+            "afmt": '{{FrontSide}}<hr id="answer"><strong>{{Pinyin}}</strong><br>{{English}}',
+        },
+    ],
+    css=CSS,
+)
 
-def process_files():
-    print("Select data file:")
-    files = []
-    for n, file in enumerate(INPUT.glob('**/*.txt')):
-        files.append(file)
-        print(f"{n+1} - {file.relative_to(INPUT)}")
-    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)}]: ")
-    in_file = files[int(s)-1]
-    relative = in_file.relative_to(INPUT)
-    out_file = OUTPUT / relative
-    out_file.parent.mkdir(parents=True, exist_ok=True)
-    return in_file, out_file
 
-def dictionary_process(in_file, out_file):
+## Functions
-    """Process dictionary files"""
+
+
+def create_cedict():
+    """Creates a create_cedict dictionary object"""
     parser = CedictParser()
     parser.read_file(CCCEDICT)
     entries = parser.parse()
@@ -61,16 +97,48 @@ def dictionary_process(in_file, out_file):
         else:
             dictionary[entry.simplified].append(entry)
 
-    out_file = DATA / f"{in_file.stem}.tsv"
+    return dictionary
-    words_list = in_file.open(encoding="utf8").read().split()
 
+
+def create_translator():
+    """Download and install Argos Translate package"""
+    argostranslate.package.update_package_index()
+    available_packages = argostranslate.package.get_available_packages()
+    package_to_install = next(
+        filter(lambda x: x.from_code == CN and x.to_code == EN, available_packages)
+    )
+    argostranslate.package.install_from_path(package_to_install.download())
+
+
+## Main
+
+
+def process_files():
+    print("Select data file:")
+    files = []
+    for n, file in enumerate(INPUT.glob("**/*.txt")):
+        files.append(file)
+        print(f"{n+1} - {file.relative_to(INPUT)}")
+    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)}]: ")
+    in_file = files[int(s) - 1]
+    relative = in_file.relative_to(INPUT)
+    out_file = OUTPUT / relative
+    out_file.parent.mkdir(parents=True, exist_ok=True)
+    with in_file.open(encoding="utf8") as input_file:
+        file_type = input_file.read().split()[0]
+    return in_file, out_file, file_type
+
+
+def dictionary_process(dictionary, in_file):
+    """Process dictionary files"""
+    words_list = in_file.open(encoding="utf8").read().split()
     results = []
     for word in words_list:
         if v := dictionary.get(word):
             if len(v) > 1:
-                print(
+                print(f"\nWARNING: {word} has multiple meanings:")
-                    f"\nWARNING: {word} has multiple meanings:"
-                )
                 for n, w in enumerate(v):
                     print(f"{n+1} - {w}")
                     for m in w.meanings:
@@ -86,7 +154,26 @@ def dictionary_process(in_file, out_file):
             print("============================================")
             print(f"===================>ERROR: {word} not found")
             print("============================================")
-    with out_file.open("w", encoding="utf8", newline="") as csvfile:
+    return results
+
+
+def trasnlator_process(in_file):
+    """Process text trasnlate files"""
+    text_list = in_file.open(encoding="utf8").read().split()[1:]
+    results = []
+    for text in text_list:
+        text = text.strip()
+        for par in text.split("。"):
+            if par:
+                translatedText = argostranslate.translate.translate(par, CN, EN)
+                results.append([translatedText, par])
+    return results
+
+
+def output_tsv(out_file, results):
+    """writes the output as a tsv file"""
+    final_file = out_file.parent / f"{out_file.stem}.tsv"
+    with final_file.open("w", encoding="utf8", newline="") as csvfile:
         writer = csv.writer(csvfile, delimiter="\t", quotechar='"')
         for entry in results:
             writer.writerow(
@@ -98,9 +185,49 @@ def dictionary_process(in_file, out_file):
                 ]
             )
 
+
+def output_anki_dictionary(out_file, results):
+    final_file = out_file.parent / f"{out_file.stem}.apkg"
+    deck_name = "::".join(out_file.relative_to(OUTPUT).parts[:-1] + (out_file.stem,))
+    deck = Deck(random.randrange(1 << 30, 1 << 31), deck_name)
+    for entry in results:
+        note = Note(
+            model=HSK_MODEL,
+            fields=[
+                "\n ".join(f"{n+1}. {m}" for n, m in enumerate(entry.meanings)),
+                PinyinToneConverter().convert_text(entry.pinyin),
+                entry.simplified,
+                entry.traditional,
+            ],
+        )
+        deck.add_note(note)
+    Package(deck).write_to_file(final_file)
+
+
+def output_anki_text(out_file, results):
+    final_file = out_file.parent / f"{out_file.stem}.apkg"
+    deck_name = "::".join(out_file.relative_to(OUTPUT).parts[:-1] + (out_file.stem,))
+    deck = Deck(random.randrange(1 << 30, 1 << 31), deck_name)
+    for entry in results:
+        note = Note(
+            model=SIMPLE_MODEL,
+            fields=entry,
+        )
+        deck.add_note(note)
+    Package(deck).write_to_file(final_file)
+
+
 def main():
-    in_file, out_file = process_files()
+    in_file, out_file, file_type = process_files()
-    dictionary_process(in_file, out_file)
+    if TEXT_TYPE == file_type:
+        create_translator()
+        results = trasnlator_process(in_file)
+        output_anki_text(out_file, results)
+    else:
+        dictionary = create_cedict()
+        results = dictionary_process(dictionary, in_file)
+        output_anki_dictionary(out_file, results)
+
 
 if __name__ == "__main__":
     main()

data/input/口语/口语-第9课.-text.txt

@@ -0,0 +1,2 @@
+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。