File size: 11,243 Bytes
982ec2b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | """
Database module for the Construction Intelligence Hub.
Handles SQLite database creation, CRUD operations, and queries.
"""
import sqlite3
import json
import os
from datetime import datetime
from typing import Optional, List, Dict, Any
from contextlib import contextmanager
DATABASE_PATH = os.getenv("DATABASE_PATH", "/data/construction_hub.db")
def get_db_path():
return DATABASE_PATH
@contextmanager
def get_connection():
"""Context manager for database connections."""
db_path = get_db_path()
os.makedirs(os.path.dirname(db_path), exist_ok=True)
conn = sqlite3.connect(db_path)
conn.row_factory = sqlite3.Row
conn.execute("PRAGMA journal_mode=WAL")
conn.execute("PRAGMA foreign_keys=ON")
try:
yield conn
conn.commit()
except Exception:
conn.rollback()
raise
finally:
conn.close()
def init_database():
"""Initialize the database schema."""
with get_connection() as conn:
conn.executescript("""
CREATE TABLE IF NOT EXISTS emails (
id INTEGER PRIMARY KEY AUTOINCREMENT,
message_id TEXT UNIQUE NOT NULL,
subject TEXT,
sender TEXT,
recipients TEXT,
date_received TIMESTAMP,
date_processed TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
body_text TEXT,
body_html TEXT,
project_name TEXT,
document_type TEXT,
document_reference_number TEXT,
status TEXT,
consultant_comments TEXT,
action_required TEXT,
assigned_discipline TEXT,
priority TEXT DEFAULT 'Normal',
ai_raw_response TEXT,
processing_status TEXT DEFAULT 'pending',
processing_error TEXT,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE IF NOT EXISTS attachments (
id INTEGER PRIMARY KEY AUTOINCREMENT,
email_id INTEGER NOT NULL,
filename TEXT NOT NULL,
mime_type TEXT,
file_size INTEGER,
file_path TEXT,
processed_by_ai BOOLEAN DEFAULT 0,
processing_error TEXT,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
FOREIGN KEY (email_id) REFERENCES emails(id) ON DELETE CASCADE
);
CREATE INDEX IF NOT EXISTS idx_emails_message_id ON emails(message_id);
CREATE INDEX IF NOT EXISTS idx_emails_document_type ON emails(document_type);
CREATE INDEX IF NOT EXISTS idx_emails_status ON emails(status);
CREATE INDEX IF NOT EXISTS idx_emails_date_received ON emails(date_received);
CREATE INDEX IF NOT EXISTS idx_emails_processing_status ON emails(processing_status);
CREATE INDEX IF NOT EXISTS idx_attachments_email_id ON attachments(email_id);
""")
def email_exists(message_id: str) -> bool:
"""Check if an email has already been processed."""
with get_connection() as conn:
cursor = conn.execute(
"SELECT 1 FROM emails WHERE message_id = ?", (message_id,)
)
return cursor.fetchone() is not None
def insert_email(email_data: Dict[str, Any]) -> int:
"""Insert a new email record and return its ID."""
with get_connection() as conn:
cursor = conn.execute("""
INSERT INTO emails (
message_id, subject, sender, recipients, date_received,
body_text, body_html, processing_status
) VALUES (?, ?, ?, ?, ?, ?, ?, ?)
""", (
email_data["message_id"],
email_data.get("subject"),
email_data.get("sender"),
email_data.get("recipients"),
email_data.get("date_received"),
email_data.get("body_text"),
email_data.get("body_html"),
"pending"
))
return cursor.lastrowid
def update_email_ai_results(email_id: int, ai_results: Dict[str, Any]):
"""Update an email record with AI extraction results."""
with get_connection() as conn:
conn.execute("""
UPDATE emails SET
project_name = ?,
document_type = ?,
document_reference_number = ?,
status = ?,
consultant_comments = ?,
action_required = ?,
assigned_discipline = ?,
priority = ?,
ai_raw_response = ?,
processing_status = 'processed',
updated_at = CURRENT_TIMESTAMP
WHERE id = ?
""", (
ai_results.get("project_name"),
ai_results.get("document_type"),
ai_results.get("document_reference_number"),
ai_results.get("status"),
ai_results.get("consultant_comments"),
ai_results.get("action_required"),
ai_results.get("assigned_discipline"),
ai_results.get("priority", "Normal"),
json.dumps(ai_results),
email_id
))
def mark_email_failed(email_id: int, error_message: str):
"""Mark an email as failed processing."""
with get_connection() as conn:
conn.execute("""
UPDATE emails SET
processing_status = 'failed',
processing_error = ?,
updated_at = CURRENT_TIMESTAMP
WHERE id = ?
""", (error_message, email_id))
def insert_attachment(email_id: int, attachment_data: Dict[str, Any]) -> int:
"""Insert an attachment record."""
with get_connection() as conn:
cursor = conn.execute("""
INSERT INTO attachments (
email_id, filename, mime_type, file_size, file_path
) VALUES (?, ?, ?, ?, ?)
""", (
email_id,
attachment_data["filename"],
attachment_data.get("mime_type"),
attachment_data.get("file_size"),
attachment_data.get("file_path")
))
return cursor.lastrowid
def mark_attachment_processed(attachment_id: int, success: bool, error: str = None):
"""Mark an attachment as processed or failed."""
with get_connection() as conn:
conn.execute("""
UPDATE attachments SET
processed_by_ai = ?,
processing_error = ?
WHERE id = ?
""", (1 if success else 0, error, attachment_id))
def get_all_emails(
document_type: Optional[str] = None,
status: Optional[str] = None,
discipline: Optional[str] = None,
search_query: Optional[str] = None,
limit: int = 500,
offset: int = 0
) -> List[Dict[str, Any]]:
"""Get all processed emails with optional filters."""
query = "SELECT * FROM emails WHERE processing_status = 'processed'"
params = []
if document_type:
query += " AND document_type = ?"
params.append(document_type)
if status:
query += " AND status = ?"
params.append(status)
if discipline:
query += " AND assigned_discipline = ?"
params.append(discipline)
if search_query:
query += " AND (subject LIKE ? OR document_reference_number LIKE ? OR consultant_comments LIKE ?)"
params.extend([f"%{search_query}%"] * 3)
query += " ORDER BY date_received DESC LIMIT ? OFFSET ?"
params.extend([limit, offset])
with get_connection() as conn:
rows = conn.execute(query, params).fetchall()
return [dict(row) for row in rows]
def get_email_by_id(email_id: int) -> Optional[Dict[str, Any]]:
"""Get a single email by ID."""
with get_connection() as conn:
row = conn.execute("SELECT * FROM emails WHERE id = ?", (email_id,)).fetchone()
return dict(row) if row else None
def get_attachments_for_email(email_id: int) -> List[Dict[str, Any]]:
"""Get all attachments for an email."""
with get_connection() as conn:
rows = conn.execute(
"SELECT * FROM attachments WHERE email_id = ?", (email_id,)
).fetchall()
return [dict(row) for row in rows]
def get_dashboard_stats() -> Dict[str, Any]:
"""Get statistics for the dashboard."""
with get_connection() as conn:
stats = {}
row = conn.execute(
"SELECT COUNT(*) as cnt FROM emails WHERE processing_status = 'processed'"
).fetchone()
stats["total_processed"] = row["cnt"]
rows = conn.execute("""
SELECT document_type, COUNT(*) as cnt
FROM emails WHERE processing_status = 'processed'
GROUP BY document_type
""").fetchall()
stats["by_document_type"] = {r["document_type"]: r["cnt"] for r in rows}
rows = conn.execute("""
SELECT status, COUNT(*) as cnt
FROM emails WHERE processing_status = 'processed'
GROUP BY status
""").fetchall()
stats["by_status"] = {r["status"]: r["cnt"] for r in rows}
rows = conn.execute("""
SELECT assigned_discipline, COUNT(*) as cnt
FROM emails WHERE processing_status = 'processed'
GROUP BY assigned_discipline
""").fetchall()
stats["by_discipline"] = {r["assigned_discipline"]: r["cnt"] for r in rows}
row = conn.execute(
"SELECT COUNT(*) as cnt FROM emails WHERE processing_status = 'pending'"
).fetchone()
stats["pending"] = row["cnt"]
row = conn.execute(
"SELECT COUNT(*) as cnt FROM emails WHERE processing_status = 'failed'"
).fetchone()
stats["failed"] = row["cnt"]
rows = conn.execute("""
SELECT DATE(date_received) as day, COUNT(*) as cnt
FROM emails WHERE processing_status = 'processed'
AND date_received >= DATE('now', '-7 days')
GROUP BY DATE(date_received)
ORDER BY day
""").fetchall()
stats["recent_activity"] = {r["day"]: r["cnt"] for r in rows}
return stats
def get_all_emails_for_export(
document_type: Optional[str] = None,
status: Optional[str] = None,
discipline: Optional[str] = None,
) -> List[Dict[str, Any]]:
"""Get all emails for CSV/Excel export (no limit)."""
query = """
SELECT
date_received, subject, sender, project_name, document_type,
document_reference_number, status, assigned_discipline,
consultant_comments, action_required, priority
FROM emails
WHERE processing_status = 'processed'
"""
params = []
if document_type:
query += " AND document_type = ?"
params.append(document_type)
if status:
query += " AND status = ?"
params.append(status)
if discipline:
query += " AND assigned_discipline = ?"
params.append(discipline)
query += " ORDER BY date_received DESC"
with get_connection() as conn:
rows = conn.execute(query, params).fetchall()
return [dict(row) for row in rows]
|