Update 日次RA.py

日次RA.py

@@ -1,181 +1,204 @@
-import streamlit as st
-import pymysql
-import json
-from datetime import datetime
-from sudachipy import dictionary, tokenizer
-from sentence_transformers import SentenceTransformer, util
-import pandas as pd  
-import os
-
-# ============================
-# 🔧 1. 設定
-# ============================
-
-# DB接続
-conn = pymysql.connect(
-    host='localhost',
-    user='user',
-    password='pass',
-    db='ra_db',
-    charset='utf8mb4',
-    autocommit=True
-)
-cur = conn.cursor()
-
-# SudachiPy セットアップ
-sudachi_tokenizer = dictionary.Dictionary().create()
-def sudachi_tokenizer_func(text):
-    tokens = sudachi_tokenizer.tokenize(text, tokenizer.Tokenizer.SplitMode.C)
-    return [t.surface() for t in tokens]
-
-# SentenceTransformerモデル
-model = SentenceTransformer("all-MiniLM-L12-v2")
-
-# 正規化辞書
-NORMALIZE = {
-    "重機": ["ショベルカー", "ユンボ", "バックホウ", "グレーダー"],
-    "作業員": ["作業者", "職人", "人"],
-    "クレーン": ["クレーン車", "吊り上げ機"],
-    "足場": ["仮設足場", "高所足場"],
-    "吊荷": ["荷", "吊り荷", "吊下げ物"]
-}
-
-# 分類キーワード
-OBJECTS = ["作業員", "重機", "クレーン", "吊荷", "足場", "ダンプ"]
-RISKS = ["挟まれ", "接触", "墜落", "転倒", "感電", "落下", "衝突"]
-
-POTENTIAL_RISKS = {
-    ("作業員", "重機"): "作業員と重機が近接している状態",
-    ("作業員", "足場"): "作業員が高所作業中の可能性",
-    ("クレーン", "吊荷"): "吊荷の下に人がいる可能性",
-    ("作業員", "吊荷"): "作業員が吊荷の下にいる可能性",
-}
-
-# ============================
-# 🧩 2. 関数群
-# ============================
-
-def normalize_text(text):
-    """表記ゆれ統一"""
-    for base, words in NORMALIZE.items():
-        for w in words:
-            text = text.replace(w, base)
-    return text
-
-def extract_relations(text):
-    """
-    文中の対象物とリスクを組み合わせて簡易ペア抽出
-    """
-    pairs = []
-    text_norm = normalize_text(text)
-
-    # 文中の対象物を検出
-    found_objects = [obj for obj in OBJECTS if obj in text_norm]
-
-    # 文中のリスクワードを検出
-    found_risks = [risk for risk in RISKS if risk in text_norm]
-
-    # 複数対象物とリスクがある場合にペア化
-    if len(found_objects) >= 2 and found_risks:
-        for i in range(len(found_objects)):
-            for j in range(i+1, len(found_objects)):
-                pairs.append((found_objects[i], found_objects[j], found_risks))
-    return pairs
-
-def generate_rules(data):
-    """ルールベース生成"""
-    text = normalize_text(" ".join([
-        data["work_content"],
-        data["hazard_points"],
-        data["risk_identification"],
-        data["mitigation_measures"]
-    ]))
-
-    # 構文関係抽出
-    relations = extract_relations(text)
-
-    rules = []
-    for subj, obj, _ in relations:
-        # 潜在リスクを確認
-        risk_desc = POTENTIAL_RISKS.get((subj, obj)) or POTENTIAL_RISKS.get((obj, subj)) or []
-        rules.append({
-            "object1": subj,
-            "object2": obj,
-            "risk": risk_desc  
-        })
-    return rules
-
-# ============================
-# 🖥 3. Streamlit UI
-# ============================
-
-st.title("日次RA入力")
-
-with st.form("ra_form"):
-    work_date = st.date_input("作業日")
-    work_content = st.text_area("作業内容")
-    hazard_points = st.text_area("作業危険ポイント")
-    general_comments = st.text_area("元請コメント")
-    risk_identification = st.text_area("危険性・有害性の特定")
-    mitigation_measures = st.text_area("危険性・有害性の低減策")
-    inspection_items = st.text_area("点検事項")
-
-    submitted = st.form_submit_button("保存")
-
-# ============================
-# フォーム送信後の処理
-# ============================
-if submitted:
-    # --- 入力データを辞書にまとめる ---
-    form_data = {
-        "work_date": str(work_date),
-        "work_content": work_content,
-        "hazard_points": hazard_points,
-        "general_comments": general_comments,
-        "risk_identification": risk_identification,
-        "mitigation_measures": mitigation_measures,
-        "inspection_items": inspection_items
-    }
-
-    # --- ルール生成 ---
-    rules = generate_rules(form_data)
-
-    # --- MySQL 保存 ---
-    sql = """INSERT INTO daily_ra 
-        (work_date, work_content, hazard_points, general_comments, risk_identification, mitigation_measures, inspection_items, created_at)
-        VALUES (%s,%s,%s,%s,%s,%s,%s,NOW())"""
-    cur.execute(sql, tuple(form_data.values()))
-    daily_id = cur.lastrowid  # daily_id を取得
-
-    for r in rules:
-        sql_rule = """INSERT INTO rule_base (daily_ra_id, object1, object2, risk, created_at)
-                      VALUES (%s,%s,%s,%s,NOW())"""
-        cur.execute(sql_rule, (daily_id, r["object1"], r["object2"], json.dumps(r["risk"], ensure_ascii=False)))
-
-    conn.commit()
-    st.success("✅ 入力内容とルールベースの生成・保存が完了しました！")
-
-    # --- 表形式でルール表示 ---
-    if rules:
-        df = pd.DataFrame(rules)
-        st.subheader("🔍 生成されたルール（テーブル形式）")
-        st.dataframe(df)
-
-    # --- JSON作成（LLM連携用）＆保存 ---
-    json_data = {
-        "daily_id": daily_id,
-        "rules": rules
-    }
-
-    # JSON保存用ディレクトリ作成
-    json_dir = "json_data"
-    os.makedirs(json_dir, exist_ok=True)
-
-    # ファイル名に daily_id とタイムスタンプを付与
-    json_path = os.path.join(json_dir, f"daily_ra_{daily_id}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json")
-
-    # JSONファイルとして保存
-    with open(json_path, "w", encoding="utf-8") as f:
-        json.dump(json_data, f, ensure_ascii=False, indent=2)
-
-    st.success(f"✅ JSONファイルを保存しました: {json_path}")
+import streamlit as st
+import pymysql
+import json
+from datetime import datetime
+from sudachipy import dictionary, tokenizer
+from sentence_transformers import SentenceTransformer, util
+import pandas as pd  
+import os
+
+# ============================
+# 🔧 1. 設定
+# ============================
+
+# DB接続
+DB_HOST = os.environ.get("DB_HOST")
+DB_USER = os.environ.get("DB_USER", "user")
+DB_PASSWORD = os.environ.get("DB_PASSWORD", "pass")
+DB_NAME = os.environ.get("DB_NAME", "ra_db")
+
+# 環境変数が未設定なら、自動判定
+if not DB_HOST:
+    # Docker 内で動くなら 'mariadb'
+    # ローカル PC で動くなら '127.0.0.1'
+    import socket
+    try:
+        # Docker ネットワーク内で 'mariadb' が解決できるか試す
+        socket.gethostbyname("mariadb")
+        DB_HOST = "mariadb"
+    except socket.gaierror:
+        DB_HOST = "127.0.0.1"
+
+# ============================
+# DB 接続
+# ============================
+conn = pymysql.connect(
+    host=DB_HOST,
+    port=3306,
+    user=DB_USER,
+    password=DB_PASSWORD,
+    db=DB_NAME,
+    charset='utf8mb4',
+    autocommit=True
+)
+cur = conn.cursor()
+
+print(f"✅ Connected to database '{DB_NAME}' on host '{DB_HOST}'")
+
+# SudachiPy セットアップ
+sudachi_tokenizer = dictionary.Dictionary().create()
+def sudachi_tokenizer_func(text):
+    tokens = sudachi_tokenizer.tokenize(text, tokenizer.Tokenizer.SplitMode.C)
+    return [t.surface() for t in tokens]
+
+# SentenceTransformerモデル
+model = SentenceTransformer("all-MiniLM-L12-v2")
+
+# 正規化辞書
+NORMALIZE = {
+    "重機": ["ショベルカー", "ユンボ", "バックホウ", "グレーダー"],
+    "作業員": ["作業者", "職人", "人"],
+    "クレーン": ["クレーン車", "吊り上げ機"],
+    "足場": ["仮設足場", "高所足場"],
+    "吊荷": ["荷", "吊り荷", "吊下げ物"]
+}
+
+# 分類キーワード
+OBJECTS = ["作業員", "重機", "クレーン", "吊荷", "足場", "ダンプ"]
+RISKS = ["挟まれ", "接触", "墜落", "転倒", "感電", "落下", "衝突"]
+
+POTENTIAL_RISKS = {
+    ("作業員", "重機"): "作業員と重機が近接している状態",
+    ("作業員", "足場"): "作業員が高所作業中の可能性",
+    ("クレーン", "吊荷"): "吊荷の下に人がいる可能性",
+    ("作業員", "吊荷"): "作業員が吊荷の下にいる可能性",
+}
+
+# ============================
+# 🧩 2. 関数群
+# ============================
+
+def normalize_text(text):
+    """表記ゆれ統一"""
+    for base, words in NORMALIZE.items():
+        for w in words:
+            text = text.replace(w, base)
+    return text
+
+def extract_relations(text):
+    """
+    文中の対象物とリスクを組み合わせて簡易ペア抽出
+    """
+    pairs = []
+    text_norm = normalize_text(text)
+
+    # 文中の対象物を検出
+    found_objects = [obj for obj in OBJECTS if obj in text_norm]
+
+    # 文中のリスクワードを検出
+    found_risks = [risk for risk in RISKS if risk in text_norm]
+
+    # 複数対象物とリスクがある場合にペア化
+    if len(found_objects) >= 2 and found_risks:
+        for i in range(len(found_objects)):
+            for j in range(i+1, len(found_objects)):
+                pairs.append((found_objects[i], found_objects[j], found_risks))
+    return pairs
+
+def generate_rules(data):
+    """ルールベース生成"""
+    text = normalize_text(" ".join([
+        data["work_content"],
+        data["hazard_points"],
+        data["risk_identification"],
+        data["mitigation_measures"]
+    ]))
+
+    # 構文関係抽出
+    relations = extract_relations(text)
+
+    rules = []
+    for subj, obj, _ in relations:
+        # 潜在リスクを確認
+        risk_desc = POTENTIAL_RISKS.get((subj, obj)) or POTENTIAL_RISKS.get((obj, subj)) or []
+        rules.append({
+            "object1": subj,
+            "object2": obj,
+            "risk": risk_desc  
+        })
+    return rules
+
+# ============================
+# 🖥 3. Streamlit UI
+# ============================
+
+st.title("日次RA入力")
+
+with st.form("ra_form"):
+    work_date = st.date_input("作業日")
+    work_content = st.text_area("作業内容")
+    hazard_points = st.text_area("作業危険ポイント")
+    general_comments = st.text_area("元請コメント")
+    risk_identification = st.text_area("危険性・有害性の特定")
+    mitigation_measures = st.text_area("危険性・有害性の低減策")
+    inspection_items = st.text_area("点検事項")
+
+    submitted = st.form_submit_button("保存")
+
+# ============================
+# フォーム送信後の処理
+# ============================
+if submitted:
+    # --- 入力データを辞書にまとめる ---
+    form_data = {
+        "work_date": str(work_date),
+        "work_content": work_content,
+        "hazard_points": hazard_points,
+        "general_comments": general_comments,
+        "risk_identification": risk_identification,
+        "mitigation_measures": mitigation_measures,
+        "inspection_items": inspection_items
+    }
+
+    # --- ルール生成 ---
+    rules = generate_rules(form_data)
+
+    # --- MySQL 保存 ---
+    sql = """INSERT INTO daily_ra 
+        (work_date, work_content, hazard_points, general_comments, risk_identification, mitigation_measures, inspection_items, created_at)
+        VALUES (%s,%s,%s,%s,%s,%s,%s,NOW())"""
+    cur.execute(sql, tuple(form_data.values()))
+    daily_id = cur.lastrowid  # daily_id を取得
+
+    for r in rules:
+        sql_rule = """INSERT INTO rule_base (daily_ra_id, object1, object2, risk, created_at)
+                      VALUES (%s,%s,%s,%s,NOW())"""
+        cur.execute(sql_rule, (daily_id, r["object1"], r["object2"], json.dumps(r["risk"], ensure_ascii=False)))
+
+    conn.commit()
+    st.success("✅ 入力内容とルールベースの生成・保存が完了しました！")
+
+    # --- 表形式でルール表示 ---
+    if rules:
+        df = pd.DataFrame(rules)
+        st.subheader("🔍 生成されたルール（テーブル形式）")
+        st.dataframe(df)
+
+    # --- JSON作成（LLM連携用）＆保存 ---
+    json_data = {
+        "daily_id": daily_id,
+        "rules": rules
+    }
+
+    # JSON保存用ディレクトリ作成
+    json_dir = "json_data"
+    os.makedirs(json_dir, exist_ok=True)
+
+    # ファイル名に daily_id とタイムスタンプを付与
+    json_path = os.path.join(json_dir, f"daily_ra_{daily_id}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json")
+
+    # JSONファイルとして保存
+    with open(json_path, "w", encoding="utf-8") as f:
+        json.dump(json_data, f, ensure_ascii=False, indent=2)
+
+    st.success(f"✅ JSONファイルを保存しました: {json_path}")