192 lines
6.2 KiB
Python
192 lines
6.2 KiB
Python
# -*- coding: utf-8 -*-
|
|||
|
|
"""
|
||
|
|
把 KaoYan_3.json(逐行 JSON,每行一个考研单词)导入 SQLite。
|
||
|
|
|
||
|
|
- 输入:本目录下的 KaoYan_3.json
|
||
|
|
- 输出:本目录下的 kao_yan_3.db
|
||
|
|
|
||
|
|
表结构:
|
||
|
|
words 单词主表(序号、单词、音标、发音标识)
|
||
|
|
word_trans 释义(词性 / 中释 / 英释)
|
||
|
|
word_sentences 例句(英文 / 中文)
|
||
|
|
word_phrases 短语(短语 / 释义)
|
||
|
|
word_synos 同近义词(词性 / 释义 / 同义词)
|
||
|
|
word_relwords 同根词(词性 / 同根词 / 释义)
|
||
|
|
|
||
|
|
可直接重跑(会先删旧表重建)。
|
||
|
|
"""
|
||
|
|
import json
|
||
|
|
import os
|
||
|
|
import sqlite3
|
||
|
|
|
||
|
|
BASE = os.path.dirname(os.path.abspath(__file__))
|
||
|
|
SRC = os.path.join(BASE, "KaoYan_3.json")
|
||
|
|
DB = os.path.join(BASE, "kao_yan_3.db")
|
||
|
|
|
||
|
|
SCHEMA = """
|
||
|
|
DROP TABLE IF EXISTS word_relwords;
|
||
|
|
DROP TABLE IF EXISTS word_synos;
|
||
|
|
DROP TABLE IF EXISTS word_phrases;
|
||
|
|
DROP TABLE IF EXISTS word_sentences;
|
||
|
|
DROP TABLE IF EXISTS word_trans;
|
||
|
|
DROP TABLE IF EXISTS words;
|
||
|
|
|
||
|
|
CREATE TABLE words (
|
||
|
|
word_id TEXT PRIMARY KEY, -- 词条ID,如 KaoYan_3_1
|
||
|
|
word_rank INTEGER NOT NULL, -- 单词序号 1..3728
|
||
|
|
head_word TEXT NOT NULL, -- 单词本身
|
||
|
|
book_id TEXT NOT NULL, -- 词库标识 KaoYan_3
|
||
|
|
ukphone TEXT, -- 英音音标
|
||
|
|
usphone TEXT, -- 美音音标
|
||
|
|
ukspeech TEXT, -- 英音发音标识
|
||
|
|
usspeech TEXT -- 美音发音标识
|
||
|
|
);
|
||
|
|
|
||
|
|
CREATE TABLE word_trans (
|
||
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
|
|
word_id TEXT NOT NULL,
|
||
|
|
pos TEXT, -- 词性
|
||
|
|
tran_cn TEXT, -- 中文释义
|
||
|
|
tran_other TEXT, -- 英文释义
|
||
|
|
sort INTEGER NOT NULL DEFAULT 0
|
||
|
|
);
|
||
|
|
|
||
|
|
CREATE TABLE word_sentences (
|
||
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
|
|
word_id TEXT NOT NULL,
|
||
|
|
s_content TEXT, -- 英文例句
|
||
|
|
s_cn TEXT, -- 例句中文
|
||
|
|
sort INTEGER NOT NULL DEFAULT 0
|
||
|
|
);
|
||
|
|
|
||
|
|
CREATE TABLE word_phrases (
|
||
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
|
|
word_id TEXT NOT NULL,
|
||
|
|
p_content TEXT, -- 短语
|
||
|
|
p_cn TEXT, -- 短语释义
|
||
|
|
sort INTEGER NOT NULL DEFAULT 0
|
||
|
|
);
|
||
|
|
|
||
|
|
CREATE TABLE word_synos (
|
||
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
|
|
word_id TEXT NOT NULL,
|
||
|
|
pos TEXT, -- 词性
|
||
|
|
tran TEXT, -- 该组释义
|
||
|
|
hwd TEXT, -- 同义词
|
||
|
|
sort INTEGER NOT NULL DEFAULT 0
|
||
|
|
);
|
||
|
|
|
||
|
|
CREATE TABLE word_relwords (
|
||
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
|
|
word_id TEXT NOT NULL,
|
||
|
|
pos TEXT, -- 词性
|
||
|
|
hwd TEXT, -- 同根词
|
||
|
|
tran TEXT, -- 释义
|
||
|
|
sort INTEGER NOT NULL DEFAULT 0
|
||
|
|
);
|
||
|
|
|
||
|
|
CREATE INDEX idx_trans_word ON word_trans(word_id);
|
||
|
|
CREATE INDEX idx_sent_word ON word_sentences(word_id);
|
||
|
|
CREATE INDEX idx_phrase_word ON word_phrases(word_id);
|
||
|
|
CREATE INDEX idx_syno_word ON word_synos(word_id);
|
||
|
|
CREATE INDEX idx_rel_word ON word_relwords(word_id);
|
||
|
|
"""
|
||
|
|
|
||
|
|
|
||
|
|
def parse_line(line):
|
||
|
|
"""把一行 JSON 解析为 (words 行, trans 列表, sentences 列表, phrases 列表, synos 列表, relwords 列表)。"""
|
||
|
|
obj = json.loads(line)
|
||
|
|
word = obj["content"]["word"]
|
||
|
|
c = word["content"]
|
||
|
|
|
||
|
|
words_row = (
|
||
|
|
word["wordId"],
|
||
|
|
obj["wordRank"],
|
||
|
|
obj["headWord"],
|
||
|
|
obj["bookId"],
|
||
|
|
c.get("ukphone"),
|
||
|
|
c.get("usphone"),
|
||
|
|
c.get("ukspeech"),
|
||
|
|
c.get("usspeech"),
|
||
|
|
)
|
||
|
|
|
||
|
|
trans = []
|
||
|
|
for i, t in enumerate(c.get("trans") or []):
|
||
|
|
trans.append((word["wordId"], t.get("pos"), t.get("tranCn"), t.get("tranOther"), i))
|
||
|
|
|
||
|
|
sentences = []
|
||
|
|
for i, s in enumerate((c.get("sentence") or {}).get("sentences") or []):
|
||
|
|
sentences.append((word["wordId"], s.get("sContent"), s.get("sCn"), i))
|
||
|
|
|
||
|
|
phrases = []
|
||
|
|
for i, p in enumerate((c.get("phrase") or {}).get("phrases") or []):
|
||
|
|
phrases.append((word["wordId"], p.get("pContent"), p.get("pCn"), i))
|
||
|
|
|
||
|
|
synos = []
|
||
|
|
for i, g in enumerate((c.get("syno") or {}).get("synos") or []):
|
||
|
|
for h in g.get("hwds") or []:
|
||
|
|
synos.append((word["wordId"], g.get("pos"), g.get("tran"), h.get("w"), i))
|
||
|
|
|
||
|
|
relwords = []
|
||
|
|
for i, g in enumerate((c.get("relWord") or {}).get("rels") or []):
|
||
|
|
for w in g.get("words") or []:
|
||
|
|
relwords.append((word["wordId"], g.get("pos"), w.get("hwd"), w.get("tran"), i))
|
||
|
|
|
||
|
|
return words_row, trans, sentences, phrases, synos, relwords
|
||
|
|
|
||
|
|
|
||
|
|
def main():
|
||
|
|
if not os.path.exists(SRC):
|
||
|
|
raise SystemExit(f"找不到输入文件: {SRC}")
|
||
|
|
|
||
|
|
conn = sqlite3.connect(DB)
|
||
|
|
cur = conn.cursor()
|
||
|
|
cur.executescript(SCHEMA)
|
||
|
|
|
||
|
|
n_words = n_trans = n_sent = n_phrase = n_syno = n_rel = 0
|
||
|
|
with open(SRC, "r", encoding="utf-8") as f:
|
||
|
|
for line in f:
|
||
|
|
line = line.strip()
|
||
|
|
if not line:
|
||
|
|
continue
|
||
|
|
w, tr, se, ph, sy, rw = parse_line(line)
|
||
|
|
cur.execute(
|
||
|
|
"INSERT INTO words VALUES (?,?,?,?,?,?,?,?)", w
|
||
|
|
)
|
||
|
|
cur.executemany(
|
||
|
|
"INSERT INTO word_trans (word_id, pos, tran_cn, tran_other, sort) VALUES (?,?,?,?,?)", tr
|
||
|
|
)
|
||
|
|
cur.executemany(
|
||
|
|
"INSERT INTO word_sentences (word_id, s_content, s_cn, sort) VALUES (?,?,?,?)", se
|
||
|
|
)
|
||
|
|
cur.executemany(
|
||
|
|
"INSERT INTO word_phrases (word_id, p_content, p_cn, sort) VALUES (?,?,?,?)", ph
|
||
|
|
)
|
||
|
|
cur.executemany(
|
||
|
|
"INSERT INTO word_synos (word_id, pos, tran, hwd, sort) VALUES (?,?,?,?,?)", sy
|
||
|
|
)
|
||
|
|
cur.executemany(
|
||
|
|
"INSERT INTO word_relwords (word_id, pos, hwd, tran, sort) VALUES (?,?,?,?,?)", rw
|
||
|
|
)
|
||
|
|
n_words += 1
|
||
|
|
n_trans += len(tr)
|
||
|
|
n_sent += len(se)
|
||
|
|
n_phrase += len(ph)
|
||
|
|
n_syno += len(sy)
|
||
|
|
n_rel += len(rw)
|
||
|
|
|
||
|
|
conn.commit()
|
||
|
|
conn.close()
|
||
|
|
|
||
|
|
print(f"单词数 : {n_words}")
|
||
|
|
print(f"释义条数 : {n_trans}")
|
||
|
|
print(f"例句条数 : {n_sent}")
|
||
|
|
print(f"短语条数 : {n_phrase}")
|
||
|
|
print(f"同近义条数: {n_syno}")
|
||
|
|
print(f"同根词条数: {n_rel}")
|
||
|
|
print(f"数据库 : {DB}")
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|