Build reading files from lesson folders. It works okay

build_jp101_reading.py

@@ -0,0 +1,33 @@
+from fugashi_parser import *
+
+import os
+from pathlib import Path
+import shutil
+import hashlib
+
+season_path = Path('/run/media/deck/YF8SD/Sync/Notebooks/Obsidian/Japanese/JPod101/3N_Absolute Beginner Season 2/')
+
+pos_list = list()
+with open(season_path.parent.joinpath(season_path.stem + '.md'), 'w') as out_file:
+    for file_path in sorted(season_path.iterdir()):
+        if file_path.is_file() and file_path.suffix == '.md':  # Ensure it's a file, not a subdirectory
+            #out_file = file_path.parent.parent.joinpath(file_path.parent.stem + '_READ.md')
+            with open(file_path, "r") as file:
+                #file.write("This text will be added to the end.")
+                print(f"###### [[{file_path.name}]]", file=out_file)
+                file.seek(0)
+                kanji_block = re.search(r'·+\s*KANJI(.*?)·+\s*[KANA|ROMANIZATION]', file.read(), re.DOTALL)
+                if (kanji_block):
+                    kanji_block.group(1)
+                    print( kanji_block.group(1).strip().replace('····','') , file=out_file)
+                else:
+                    print(file_path.stem, 'No Kanji block found')
+            # else:
+            #     print(pos, ' - no tag')
+
+            # with file_path.open('r') as file:
+            #     content = file.read()
+            #     print(f"Content of {file_path.name}: {content}")
+
+unique_values = list(set(pos_list))
+print(unique_values)

fugashi_parser.py

@@ -34,19 +34,19 @@ KATAKANA_TO_HIRAGANA_OFFSET = ord("ぁ") - ord("ァ")
 
 CONTENT_POS1 = {"名詞", "動詞", "形容詞", "形状詞", "副詞", "代名詞"}
 
-def is_vocab_token(pos, keep_pronouns=False, keep_numbers=False):
+# def is_vocab_token(pos, keep_pronouns=False, keep_numbers=False):
-    pos1, pos2, pos3, pos4 = pos
+#     pos1, pos2, pos3, pos4 = pos
 
-    if pos1 not in CONTENT_POS1:
+#     if pos1 not in CONTENT_POS1:
-        return False
+#         return False
 
-    if pos1 == "代名詞" and not keep_pronouns:
+#     if pos1 == "代名詞" and not keep_pronouns:
-        return False
+#         return False
 
-    if pos1 == "名詞" and pos2 == "数詞" and not keep_numbers:
+#     if pos1 == "名詞" and pos2 == "数詞" and not keep_numbers:
-        return False
+#         return False
 
-    return True
+#     return True
 
 
 
@@ -148,7 +148,7 @@ def build_kana(surface: str, reading: str) -> str:
 
 def build_vocab_link(surface: str, reading: str, pos) -> str:
     pos1, pos2, pos3, pos4 = pos
-    if not is_vocab_token(pos, keep_pronouns=True,keep_numbers=False):
+    if not is_vocab_token(surface, pos, keep_pronouns=True,keep_numbers=False):
         return surface
     # if surface == reading:
     #     return f"[[{surface}]]"
@@ -232,7 +232,7 @@ def chunk_predicates(tokens):
     return chunks
 
 ## Vocab Filtering
-def is_vocab_token(pos, keep_pronouns=False, keep_numbers=False):
+def is_vocab_token(surface, pos, keep_pronouns=False, keep_numbers=False):
     pos1, pos2, pos3, pos4 = pos
 
     if pos1 not in {"名詞", "動詞", "形容詞", "形状詞", "副詞", "代名詞", "感動詞"}:
@@ -241,7 +241,7 @@ def is_vocab_token(pos, keep_pronouns=False, keep_numbers=False):
     if pos1 == "代名詞" and not keep_pronouns:
         return False
 
-    if pos1 == "名詞" and pos2 == "数詞" and not keep_numbers:
+    if pos1 == "名詞" and pos2 == "数詞" and not has_kanji(surface) and not keep_numbers:
         return False
 
     return True
@@ -299,7 +299,7 @@ def update_vocab(vocab: Dict[str, Dict], tokens: List[TokenReading]):
 
         # if should_skip(t.surface, pos1) or not is_content_word(pos1):
         #     continue
-        if not is_vocab_token(t.pos, keep_pronouns=True,keep_numbers=False):
+        if not is_vocab_token(t.surface, t.pos, keep_pronouns=True,keep_numbers=False):
             continue
 
         entry = vocab.get(t.lemma)