Update: 初学记、佩文韵府 and 五车韵瑞

初学记/test_split.py

@@ -0,0 +1,41 @@
+import re
+
+def extract_sections(content_text):
+    result = {"叙事": "", "事对": "", "诗文": ""}
+
+    rest_after_narrative = content_text
+
+    shìduì_start = rest_after_narrative.find("事對")
+    if shìduì_start == -1:
+        shìduì_start = rest_after_narrative.find("事对")
+
+    genre_pattern = r"〉(賦|詩|讚|表|碑|頌|銘|檄|文|啓|書|歌|曲|引|記|箴|七|連珠|弔|祭文|詔|令|誄|序|論|賛|讃|啟|辭|辞|操|對|对|銘|論)"
+
+    if shìduì_start != -1:
+        result["叙事"] = rest_after_narrative[:shìduì_start]
+        rest_after_shiduì = rest_after_narrative[shìduì_start + 2 :]
+
+        shiwen_match = re.search(genre_pattern, rest_after_shiduì)
+
+        if shiwen_match:
+            split_idx = shiwen_match.start() + 1
+            result["事对"] = rest_after_shiduì[:split_idx]
+            result["诗文"] = rest_after_shiduì[split_idx:]
+        else:
+            result["事对"] = rest_after_shiduì
+    else:
+        shiwen_match = re.search(genre_pattern, rest_after_narrative)
+        if shiwen_match:
+            split_idx = shiwen_match.start() + 1
+            result["叙事"] = rest_after_narrative[:split_idx]
+            result["诗文"] = rest_after_narrative[split_idx:]
+        else:
+            result["叙事"] = rest_after_narrative
+
+    for k in result:
+        result[k] = result[k].replace("〈", "（").replace("〉", "）")
+
+    return result
+
+import json
+print(extract_sections("這里是叙事事對這裡是事對〉詩這里是詩文"))