Commit inicial - upload de todos os arquivos da pasta

This commit is contained in:
2026-07-24 15:51:10 -03:00
commit efa06def71
44 changed files with 3604 additions and 0 deletions
+508
View File
@@ -0,0 +1,508 @@
"""Acesso ao SQLite: esquema, migrações leves e helpers de consulta.
Estende o esquema original (uploaded_files -> detected_documents -> fiscal_documents)
com autenticação (users), lotes de importação (import_batches) e os campos de
legibilidade usados pela extração por IA.
"""
from __future__ import annotations
import json
import sqlite3
from contextlib import contextmanager
from pathlib import Path
from typing import Any, Iterator
from .config import get_settings
SCHEMA = """
CREATE TABLE IF NOT EXISTS users (
id INTEGER PRIMARY KEY AUTOINCREMENT,
username TEXT NOT NULL UNIQUE,
password_hash TEXT NOT NULL,
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE IF NOT EXISTS import_batches (
id INTEGER PRIMARY KEY AUTOINCREMENT,
status TEXT NOT NULL DEFAULT 'open',
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
confirmed_at TEXT
);
CREATE TABLE IF NOT EXISTS uploaded_files (
id INTEGER PRIMARY KEY AUTOINCREMENT,
batch_id INTEGER REFERENCES import_batches(id) ON DELETE SET NULL,
original_name TEXT NOT NULL,
stored_path TEXT NOT NULL,
content_type TEXT NOT NULL,
size_bytes INTEGER NOT NULL,
status TEXT NOT NULL DEFAULT 'pending',
detected_count INTEGER NOT NULL DEFAULT 0,
message TEXT,
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE IF NOT EXISTS detected_documents (
id INTEGER PRIMARY KEY AUTOINCREMENT,
upload_id INTEGER NOT NULL REFERENCES uploaded_files(id) ON DELETE CASCADE,
batch_id INTEGER REFERENCES import_batches(id) ON DELETE SET NULL,
source_file_name TEXT NOT NULL,
source_page INTEGER,
source_location TEXT NOT NULL,
raw_text TEXT NOT NULL DEFAULT '',
purchase_date TEXT,
supplier_name TEXT,
total_paid REAL,
confidence TEXT NOT NULL DEFAULT 'low',
field_confidence_json TEXT NOT NULL DEFAULT '{}',
legible INTEGER NOT NULL DEFAULT 1,
uncertain_fields TEXT NOT NULL DEFAULT '[]',
extractor TEXT NOT NULL DEFAULT 'local',
status TEXT NOT NULL DEFAULT 'staged',
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE IF NOT EXISTS fiscal_documents (
id INTEGER PRIMARY KEY AUTOINCREMENT,
detected_document_id INTEGER REFERENCES detected_documents(id) ON DELETE SET NULL,
source_file_name TEXT NOT NULL DEFAULT '',
source_location TEXT NOT NULL DEFAULT '',
purchase_date TEXT NOT NULL,
supplier_name TEXT NOT NULL,
total_paid REAL NOT NULL,
confidence TEXT NOT NULL DEFAULT 'high',
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP
);
CREATE INDEX IF NOT EXISTS idx_fiscal_date ON fiscal_documents(purchase_date);
CREATE INDEX IF NOT EXISTS idx_detected_batch ON detected_documents(batch_id, status);
"""
def connect(db_path: Path | None = None) -> sqlite3.Connection:
settings = get_settings()
settings.ensure_storage()
conn = sqlite3.connect(db_path or settings.db_path)
conn.row_factory = sqlite3.Row
conn.execute("PRAGMA foreign_keys = ON")
conn.execute("PRAGMA journal_mode = WAL")
return conn
def init_db(conn: sqlite3.Connection) -> None:
conn.executescript(SCHEMA)
conn.commit()
@contextmanager
def session(db_path: Path | None = None) -> Iterator[sqlite3.Connection]:
conn = connect(db_path)
try:
init_db(conn)
yield conn
finally:
conn.close()
# --------------------------------------------------------------------------- #
# Usuários
# --------------------------------------------------------------------------- #
def count_users(conn: sqlite3.Connection) -> int:
return int(conn.execute("SELECT COUNT(*) FROM users").fetchone()[0])
def get_user(conn: sqlite3.Connection, username: str) -> sqlite3.Row | None:
return conn.execute(
"SELECT * FROM users WHERE username = ?", (username,)
).fetchone()
def create_user(conn: sqlite3.Connection, username: str, password_hash: str) -> int:
cur = conn.execute(
"INSERT INTO users (username, password_hash) VALUES (?, ?)",
(username, password_hash),
)
conn.commit()
return int(cur.lastrowid)
def update_password(conn: sqlite3.Connection, username: str, password_hash: str) -> None:
conn.execute(
"UPDATE users SET password_hash = ? WHERE username = ?",
(password_hash, username),
)
conn.commit()
# --------------------------------------------------------------------------- #
# Lotes de importação
# --------------------------------------------------------------------------- #
def create_batch(conn: sqlite3.Connection) -> int:
cur = conn.execute("INSERT INTO import_batches (status) VALUES ('open')")
conn.commit()
return int(cur.lastrowid)
def get_batch(conn: sqlite3.Connection, batch_id: int) -> sqlite3.Row | None:
return conn.execute(
"SELECT * FROM import_batches WHERE id = ?", (batch_id,)
).fetchone()
def set_batch_status(conn: sqlite3.Connection, batch_id: int, status: str) -> None:
if status == "confirmed":
conn.execute(
"UPDATE import_batches SET status = ?, confirmed_at = CURRENT_TIMESTAMP WHERE id = ?",
(status, batch_id),
)
else:
conn.execute(
"UPDATE import_batches SET status = ? WHERE id = ?", (status, batch_id)
)
conn.commit()
# --------------------------------------------------------------------------- #
# Uploads
# --------------------------------------------------------------------------- #
def insert_upload(
conn: sqlite3.Connection,
batch_id: int,
original_name: str,
stored_path: Path,
content_type: str,
size_bytes: int,
) -> int:
cur = conn.execute(
"""
INSERT INTO uploaded_files (batch_id, original_name, stored_path, content_type, size_bytes)
VALUES (?, ?, ?, ?, ?)
""",
(batch_id, original_name, str(stored_path), content_type, size_bytes),
)
conn.commit()
return int(cur.lastrowid)
def update_upload_status(
conn: sqlite3.Connection,
upload_id: int,
status: str,
detected_count: int,
message: str | None = None,
) -> None:
conn.execute(
"""
UPDATE uploaded_files
SET status = ?, detected_count = ?, message = ?, updated_at = CURRENT_TIMESTAMP
WHERE id = ?
""",
(status, detected_count, message, upload_id),
)
conn.commit()
def get_upload(conn: sqlite3.Connection, upload_id: int) -> sqlite3.Row | None:
return conn.execute(
"SELECT * FROM uploaded_files WHERE id = ?", (upload_id,)
).fetchone()
# --------------------------------------------------------------------------- #
# Documentos detectados (staging)
# --------------------------------------------------------------------------- #
def insert_detected(
conn: sqlite3.Connection,
*,
upload_id: int,
batch_id: int,
source_file_name: str,
source_page: int | None,
source_location: str,
raw_text: str,
purchase_date: str | None,
supplier_name: str | None,
total_paid: float | None,
confidence: str,
field_confidence: dict[str, str],
legible: bool,
uncertain_fields: list[str],
extractor: str,
) -> int:
cur = conn.execute(
"""
INSERT INTO detected_documents (
upload_id, batch_id, source_file_name, source_page, source_location,
raw_text, purchase_date, supplier_name, total_paid, confidence,
field_confidence_json, legible, uncertain_fields, extractor, status
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, 'staged')
""",
(
upload_id,
batch_id,
source_file_name,
source_page,
source_location,
raw_text,
purchase_date,
supplier_name,
total_paid,
confidence,
json.dumps(field_confidence, ensure_ascii=False),
1 if legible else 0,
json.dumps(uncertain_fields, ensure_ascii=False),
extractor,
),
)
conn.commit()
return int(cur.lastrowid)
def get_detected(conn: sqlite3.Connection, detected_id: int) -> sqlite3.Row | None:
return conn.execute(
"SELECT * FROM detected_documents WHERE id = ?", (detected_id,)
).fetchone()
def staged_documents(conn: sqlite3.Connection, batch_id: int) -> list[sqlite3.Row]:
return list(
conn.execute(
"""
SELECT * FROM detected_documents
WHERE batch_id = ? AND status = 'staged'
ORDER BY id ASC
""",
(batch_id,),
)
)
def batch_summary(conn: sqlite3.Connection, batch_id: int) -> dict[str, Any]:
row = conn.execute(
"""
SELECT COUNT(*) AS n,
COALESCE(SUM(total_paid), 0) AS total,
SUM(CASE WHEN legible = 0 THEN 1 ELSE 0 END) AS ilegiveis,
SUM(CASE WHEN supplier_name IS NULL OR TRIM(supplier_name) = ''
OR total_paid IS NULL THEN 1 ELSE 0 END) AS incompletos
FROM detected_documents
WHERE batch_id = ? AND status = 'staged'
""",
(batch_id,),
).fetchone()
# "pendentes" = tudo que impede importar (ilegível OU faltando fornecedor/valor).
ilegiveis = int(row["ilegiveis"] or 0)
incompletos = int(row["incompletos"] or 0)
pendentes = conn.execute(
"""
SELECT COUNT(*) FROM detected_documents
WHERE batch_id = ? AND status = 'staged'
AND (legible = 0 OR supplier_name IS NULL OR TRIM(supplier_name) = '' OR total_paid IS NULL)
""",
(batch_id,),
).fetchone()[0]
return {
"count": int(row["n"]),
"total": float(row["total"]),
"ilegiveis": ilegiveis,
"incompletos": incompletos,
"pendentes": int(pendentes),
}
def update_staged(
conn: sqlite3.Connection,
detected_id: int,
*,
purchase_date: str,
supplier_name: str,
total_paid: float,
legible: bool = True,
) -> None:
conn.execute(
"""
UPDATE detected_documents
SET purchase_date = ?, supplier_name = ?, total_paid = ?,
legible = ?, updated_at = CURRENT_TIMESTAMP
WHERE id = ? AND status = 'staged'
""",
(purchase_date, supplier_name, total_paid, 1 if legible else 0, detected_id),
)
conn.commit()
def discard_staged(conn: sqlite3.Connection, detected_id: int) -> None:
conn.execute(
"UPDATE detected_documents SET status = 'discarded', updated_at = CURRENT_TIMESTAMP WHERE id = ?",
(detected_id,),
)
conn.commit()
def confirm_batch(conn: sqlite3.Connection, batch_id: int) -> int:
"""Promove todos os detectados 'staged' do lote para fiscal_documents."""
rows = staged_documents(conn, batch_id)
inserted = 0
for row in rows:
if not row["purchase_date"] or not row["supplier_name"] or row["total_paid"] is None:
# Sem os três campos essenciais não confirma — permanece staged.
continue
conn.execute(
"""
INSERT INTO fiscal_documents (
detected_document_id, source_file_name, source_location,
purchase_date, supplier_name, total_paid, confidence
) VALUES (?, ?, ?, ?, ?, ?, ?)
""",
(
row["id"],
row["source_file_name"],
row["source_location"],
row["purchase_date"],
row["supplier_name"],
float(row["total_paid"]),
row["confidence"],
),
)
conn.execute(
"UPDATE detected_documents SET status = 'confirmed', updated_at = CURRENT_TIMESTAMP WHERE id = ?",
(row["id"],),
)
inserted += 1
set_batch_status(conn, batch_id, "confirmed")
conn.commit()
return inserted
# --------------------------------------------------------------------------- #
# CRUD de fiscal_documents
# --------------------------------------------------------------------------- #
def create_fiscal(
conn: sqlite3.Connection,
*,
purchase_date: str,
supplier_name: str,
total_paid: float,
source_file_name: str = "lançamento manual",
source_location: str = "manual",
confidence: str = "high",
detected_document_id: int | None = None,
) -> int:
cur = conn.execute(
"""
INSERT INTO fiscal_documents (
detected_document_id, source_file_name, source_location,
purchase_date, supplier_name, total_paid, confidence
) VALUES (?, ?, ?, ?, ?, ?, ?)
""",
(
detected_document_id,
source_file_name,
source_location,
purchase_date,
supplier_name,
total_paid,
confidence,
),
)
conn.commit()
return int(cur.lastrowid)
def get_fiscal(conn: sqlite3.Connection, doc_id: int) -> sqlite3.Row | None:
return conn.execute(
"SELECT * FROM fiscal_documents WHERE id = ?", (doc_id,)
).fetchone()
def update_fiscal(
conn: sqlite3.Connection,
doc_id: int,
*,
purchase_date: str,
supplier_name: str,
total_paid: float,
) -> None:
conn.execute(
"""
UPDATE fiscal_documents
SET purchase_date = ?, supplier_name = ?, total_paid = ?, updated_at = CURRENT_TIMESTAMP
WHERE id = ?
""",
(purchase_date, supplier_name, total_paid, doc_id),
)
conn.commit()
def delete_fiscal(conn: sqlite3.Connection, doc_id: int) -> None:
conn.execute("DELETE FROM fiscal_documents WHERE id = ?", (doc_id,))
conn.commit()
def list_fiscal(
conn: sqlite3.Connection,
*,
start: str | None = None,
end: str | None = None,
supplier: str | None = None,
) -> list[sqlite3.Row]:
clauses: list[str] = []
params: list[Any] = []
if start:
clauses.append("purchase_date >= ?")
params.append(start)
if end:
clauses.append("purchase_date <= ?")
params.append(end)
if supplier:
clauses.append("supplier_name LIKE ?")
params.append(f"%{supplier}%")
where = f"WHERE {' AND '.join(clauses)}" if clauses else ""
return list(
conn.execute(
f"SELECT * FROM fiscal_documents {where} ORDER BY purchase_date DESC, id DESC",
params,
)
)
def monthly_totals(conn: sqlite3.Connection) -> list[sqlite3.Row]:
return list(
conn.execute(
"""
SELECT substr(purchase_date, 1, 7) AS month, SUM(total_paid) AS total, COUNT(*) AS count
FROM fiscal_documents
GROUP BY substr(purchase_date, 1, 7)
ORDER BY month ASC
"""
)
)
def supplier_totals(conn: sqlite3.Connection, limit: int = 10) -> list[sqlite3.Row]:
return list(
conn.execute(
"""
SELECT supplier_name, SUM(total_paid) AS total, COUNT(*) AS count
FROM fiscal_documents
GROUP BY supplier_name
ORDER BY total DESC
LIMIT ?
""",
(limit,),
)
)
def overall_totals(conn: sqlite3.Connection) -> dict[str, Any]:
row = conn.execute(
"SELECT COUNT(*) AS n, COALESCE(SUM(total_paid), 0) AS total FROM fiscal_documents"
).fetchone()
n = int(row["n"])
total = float(row["total"])
return {"count": n, "total": total, "avg": (total / n) if n else 0.0}