Files
EnglishNotes/英语词汇/情景单词记忆/highlight_words_analysis.py
T
2026-10-04 11:13:54 +08:00

126 lines
4.4 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
"""
从词汇全表分组 md 中提取 Obsidian 高亮(==...==)词汇,
从 kao_yan_3.db 查询音标/词性释义/例句/短语/近义词,生成"高亮单词解析"
并追加到该 md 文件末尾。支持一次处理多个文件,幂等(已生成则先移除旧章节)。
用法:
python highlight_words_analysis.py [--db 路径] [--file 文件1 文件2 ...]
不带 --file 时自动处理 词汇全表 目录下所有含 ==高亮== 的 md。
"""
import argparse
import os
import re
import sqlite3
HEADER = "## 高亮单词解析"
def esc(s):
return (s or "").replace("|", "\\|").replace("\r", " ").replace("\n", " ").strip()
def parse_md(db_path, md_path):
txt = open(md_path, encoding="utf-8").read()
words = []
for m in re.finditer(r"==(.+?)==", txt):
w = m.group(1).strip()
if w and w not in words:
words.append(w)
return txt, words
def lookup(cur, word):
row = cur.execute("SELECT word_id, ukphone, usphone FROM words WHERE head_word=?", (word,)).fetchone()
if not row:
return None
wid, uk, us = row
trans = cur.execute(
"SELECT pos, tran_cn FROM word_trans WHERE word_id=? ORDER BY sort, id", (wid,)
).fetchall()
sent = cur.execute(
"SELECT s_content, s_cn FROM word_sentences WHERE word_id=? ORDER BY sort, id LIMIT 1", (wid,)
).fetchone()
phrases = cur.execute(
"SELECT p_content, p_cn FROM word_phrases WHERE word_id=? ORDER BY sort, id LIMIT 3", (wid,)
).fetchall()
synos = cur.execute(
"SELECT hwd FROM word_synos WHERE word_id=? ORDER BY sort, id LIMIT 3", (wid,)
).fetchall()
return {"phone": uk or us, "trans": trans, "sent": sent, "phrases": phrases, "synos": synos}
def build_block(word, data):
phone = f" /{esc(data['phone'])}/" if data["phone"] else ""
lines = [f"### {esc(word)}{phone}", ""]
pos_parts = [f"{p}. {esc(t)}" for p, t in data["trans"] if p or t]
if pos_parts:
lines.append(f"**词性**:{';'.join(pos_parts)}")
else:
lines.append("**词性**:—")
if data["sent"]:
s, cn = data["sent"]
lines.append(f"**例句**:{esc(s)}({esc(cn)})")
if data["phrases"]:
lines.append("**短语**:" + ";".join(f"{esc(p)} {esc(c)}" for p, c in data["phrases"]))
if data["synos"]:
lines.append("**近义**:" + ",".join(esc(s[0]) for s in data["synos"]))
lines.append("")
return "\n".join(lines)
def process(db_path, md_path):
txt = open(md_path, encoding="utf-8").read()
# 先移除旧章节(幂等),再提取高亮,避免旧章节说明文字被误提取
pat = re.compile(r"\n---\n\n" + re.escape(HEADER) + r".*$", re.S)
clean = pat.sub("", txt).rstrip() + "\n"
words = []
for m in re.finditer(r"==(.+?)==", clean):
w = m.group(1).strip()
if w and w not in words:
words.append(w)
if not words:
print(f"跳过(无高亮):{md_path}")
return 0
conn = sqlite3.connect(db_path)
cur = conn.cursor()
blocks = []
missing = []
for w in words:
data = lookup(cur, w)
if data is None:
missing.append(w)
continue
blocks.append(build_block(w, data))
conn.close()
new_sec = "\n---\n\n" + HEADER + f"({len(blocks)} 词)\n\n"
new_sec += "> 由脚本 highlight_words_analysis.py 自动提取文中高亮标记(==…==)词汇生成,数据来自 kao_yan_3.db(音标/词性/释义/例句/短语/近义词)。\n\n"
new_sec += "\n".join(blocks)
with open(md_path, "w", encoding="utf-8") as f:
f.write(clean + "\n" + new_sec + "\n")
print(f"已处理:{md_path}(高亮 {len(words)} 词,生成解析 {len(blocks)} 词,未找到 {missing})")
return len(blocks)
def main():
base = os.path.dirname(os.path.abspath(__file__))
ap = argparse.ArgumentParser()
ap.add_argument("--db", default=os.path.join(base, "kao_yan_3.db"))
ap.add_argument("--file", nargs="*", default=None)
args = ap.parse_args()
if args.file:
files = args.file
else:
d = os.path.normpath(os.path.join(base, "..", "词汇全表"))
files = [os.path.join(d, f) for f in sorted(os.listdir(d)) if f.endswith(".md")]
total = 0
for f in files:
total += process(args.db, f)
print(f"\n共生成解析 {total} 词。")
if __name__ == "__main__":
main()