Initial toolkit: scripts, references, skills, and term database

terms-database/.codegraph/.gitignore

@@ -0,0 +1,16 @@
+# CodeGraph data files
+# These are local to each machine and should not be committed
+
+# Database
+*.db
+*.db-wal
+*.db-shm
+
+# Cache
+cache/
+
+# Logs
+*.log
+
+# Hook markers
+.dirty

terms-database/.dockerignore

@@ -0,0 +1,4 @@
+.git
+**/__pycache__
+**/__pypackages__
+fly.toml

terms-database/.gitignore

@@ -0,0 +1,2 @@
+__pycache__/
+__pypackages__/

terms-database/Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.14-slim
+
+WORKDIR /app
+
+RUN pip install --no-cache-dir flask duckdb gunicorn
+
+COPY . .
+
+EXPOSE 8910
+
+CMD ["gunicorn", "-b", "0.0.0.0:8910", "-w", "1", "--timeout", "30", "server:app"]

terms-database/deploy

@@ -0,0 +1,2 @@
+#!/usr/bin/fish
+fly deploy -y --depot=false

terms-database/fly.toml

@@ -0,0 +1,20 @@
+# fly.toml app configuration file generated for buddhist-terms-search on 2026-06-09T13:38:18+08:00
+#
+# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
+#
+
+app = 'buddhist-terms-search'
+primary_region = 'sin'
+
+[http_service]
+  internal_port = 8910
+  force_https = true
+  auto_stop_machines = 'stop'
+  auto_start_machines = true
+  min_machines_running = 0
+  processes = ['app']
+
+[[vm]]
+  memory = '256mb'
+  cpus = 1
+  memory_mb = 256

terms-database/search.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+"""Full-text search over MPI term database. Queries unified_terms_flat via DuckDB LIKE.
+
+Module usage:
+    from search import search_terms
+    results = search_terms("空性")
+    results = search_terms("空性", limit=5, loc="心经", src="佛教术语")
+    # returns list of dicts: {zh, en, loc, source}
+
+CLI usage:
+    python search.py <query> [limit]
+    python search.py 空性 loc:心经 src:公案
+"""
+
+import sys
+import os
+import duckdb
+
+DB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "termlib.duckdb")
+
+
+def _connect():
+    return duckdb.connect(DB, read_only=True)
+
+
+def _search_rows(con, query, loc=None, src=None, limit=None):
+    terms = query.split() if query else []
+    clauses = []
+    params = []
+
+    for t in terms:
+        like = f"%{t}%"
+        clauses.append("(zh LIKE ? OR en LIKE ?)")
+        params.extend([like, like])
+
+    where = " AND ".join(clauses) if clauses else "1=1"
+
+    if loc:
+        where += " AND loc LIKE ?"
+        params.append(f"%{loc}%")
+    if src:
+        where += " AND source = ?"
+        params.append(src)
+
+    sql = f"SELECT zh, en, loc, source FROM unified_terms_flat WHERE {where}"
+    if limit is not None:
+        sql += " LIMIT ?"
+        params.append(limit)
+
+    return con.execute(sql, params).fetchall()
+
+
+def search(query, loc=None, src=None, limit=20):
+    """Search the terms database. Returns list of {zh, en, loc, source} dicts.
+    
+    query: str — space-separated search terms (AND logic)
+    loc: str — filter by loc column (LIKE match)
+    src: str — filter by source column (exact match)
+    limit: int — max results (default 20)
+    """
+    con = _connect()
+    try:
+        rows = _search_rows(con, query, loc=loc, src=src, limit=limit)
+        return [
+            {"zh": zh, "en": en, "loc": loc_val or "", "source": src_val}
+            for zh, en, loc_val, src_val in rows
+        ]
+    finally:
+        con.close()
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: terms-search <query> [limit]")
+        print("  queries: '空性', 'emptiness 中观'")
+        print()
+        print("Special prefixes (can be standalone or combined with query):")
+        print("  loc:<source>  — filter by loc (e.g. loc:心经)")
+        print("  src:<table>   — filter by source table (e.g. src:佛教术语)")
+        print()
+        print("Examples:")
+        print("  terms-search 空性")
+        print("  terms-search 'suffering 苦' loc:心经")
+        print("  terms-search src:公案")
+        sys.exit(1)
+
+    raw = sys.argv[1]
+    limit = int(sys.argv[2]) if len(sys.argv) > 2 else 20
+
+    loc_filter = None
+    src_filter = None
+    query_parts = []
+
+    for token in raw.split():
+        if token.startswith("loc:"):
+            loc_filter = token[4:]
+        elif token.startswith("src:"):
+            src_filter = token[4:]
+        else:
+            query_parts.append(token)
+
+    query_str = " ".join(query_parts)
+
+    if not query_str and not loc_filter and not src_filter:
+        print("No search terms or filters. Usage: terms-search <query> [limit]")
+        return
+
+    results = search(query_str, loc=loc_filter, src=src_filter, limit=limit)
+
+    if not results:
+        print(f"No results for: {raw}")
+        return
+
+    print(f"Results: {len(results)}")
+    print()
+    for r in results:
+        print(f"zh: {r['zh']}")
+        print(f"en: {r['en']}")
+        print(f"loc: {r['loc'] or '-'}  |  src: {r['source']}")
+        print()
+
+
+if __name__ == "__main__":
+    main()

terms-database/server.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+import sys, os
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
+import duckdb
+from flask import Flask, request, jsonify, render_template
+import search as s
+
+app = Flask(__name__)
+
+def do_search(q, loc, src, limit):
+    with duckdb.connect(s.DB, read_only=True) as con:
+        rows = s.search(con, q, loc, src, limit)
+    return [{'zh': r[0], 'en': r[1], 'loc': r[2] or None, 'source': r[3]} for r in rows]
+
+def do_sources():
+    with duckdb.connect(s.DB, read_only=True) as con:
+        rows = con.execute(
+            'SELECT source, COUNT(*) AS cnt FROM unified_terms_flat GROUP BY source ORDER BY cnt DESC'
+        ).fetchall()
+    return [{'source': r[0], 'count': r[1]} for r in rows]
+
+@app.route('/search')
+def search():
+    try:
+        q = request.args.get('q', '')
+        loc = request.args.get('loc')
+        src = request.args.get('src')
+        limit = request.args.get('limit', type=int)
+        results = do_search(q, loc, src, limit)
+        return jsonify({'count': len(results), 'results': results})
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/sources')
+def sources():
+    try:
+        sources = do_sources()
+        return jsonify(sources)
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/sources.html')
+def sources_html():
+    try:
+        sources = do_sources()
+        total = sum(s['count'] for s in sources)
+        return render_template('sources.html', sources=sources, total=total)
+    except Exception as e:
+        return render_template('sources.html', sources=[], total=0, error=str(e))
+
+@app.route('/')
+def ui():
+    q = request.args.get('q', '')
+    loc = request.args.get('loc', '')
+    src = request.args.get('src', '')
+    limit = request.args.get('limit', '')
+    searched = bool(request.args)
+    results = []
+    count = 0
+    error = None
+    if searched and (q or loc or src):
+        try:
+            lim = int(limit) if limit else None
+            results = do_search(q, loc or None, src or None, lim)
+            count = len(results)
+        except Exception as e:
+            error = str(e)
+    return render_template('index.html', q=q, loc=loc, src=src, limit=limit,
+                           searched=searched, results=results, count=count, error=error)
+
+if __name__ == '__main__':
+    app.run(port=8910)

terms-database/templates/index.html

@@ -0,0 +1,30 @@
+<!DOCTYPE html>
+<meta charset="utf-8">
+<title>静心学堂中英文翻译对照表</title>
+<h1>静心学堂（非官方）中英文翻译对照表</h1>
+<p><a href="/">search</a> | <a href="/sources.html">sources</a></p>
+<form method="get">
+  <input name="q" value="{{ q }}" placeholder="query (e.g. 空性 emptiness)">
+  <input name="loc" value="{{ loc }}" placeholder="loc filter">
+  <input name="src" value="{{ src }}" placeholder="src filter">
+  <input name="limit" value="{{ limit }}" size="4" placeholder="limit">
+  <button type="submit">Search</button>
+</form>
+
+{% if searched %}
+{% if error %}<p>Error: {{ error }}</p>
+{% else %}
+<p>{{ count }} results</p>
+<table border="1" cellpadding="4" cellspacing="0">
+  <tr><th>ZH</th><th>EN</th><th>LOC</th><th>SRC</th></tr>
+  {% for r in results %}
+  <tr>
+    <td>{{ r.zh }}</td>
+    <td>{{ r.en }}</td>
+    <td>{{ r.loc or '' }}</td>
+    <td>{{ r.source }}</td>
+  </tr>
+  {% endfor %}
+</table>
+{% endif %}
+{% endif %}

terms-database/templates/sources.html

@@ -0,0 +1,19 @@
+<!DOCTYPE html>
+<meta charset="utf-8">
+<title>Sources — 静心学堂翻译对照表</title>
+<h1>Sources</h1>
+<p><a href="/">search</a> | <a href="/sources.html">sources</a></p>
+
+{% if error %}<p>Error: {{ error }}</p>
+{% else %}
+<table border="1" cellpadding="4" cellspacing="0">
+  <tr><th>Source</th><th>Rows</th></tr>
+  {% for s in sources %}
+  <tr>
+    <td><a href="/?src={{ s.source }}">{{ s.source }}</a></td>
+    <td>{{ s.count }}</td>
+  </tr>
+  {% endfor %}
+  <tr><th>Total</th><th>{{ total }}</th></tr>
+</table>
+{% endif %}