Projeto do Agent Contas ORACLE

This commit is contained in:
2026-08-19 09:35:50 -03:00
commit 950a2bcd33
1366 changed files with 177217 additions and 0 deletions

View File

@@ -0,0 +1,16 @@
from __future__ import annotations
import io
from typing import Any
from .bill_parser import TimBillParser
from .bill_processor import PDFBillingProcessor
def parse_tim_bill_pdf(pdf_content: bytes, *, include_danfe: bool = False) -> dict[str, Any]:
pdf_bytes = io.BytesIO(pdf_content)
parser = TimBillParser()
dfs = parser.parse_pdf(pdf_bytes)
processor = PDFBillingProcessor(include_danfe=include_danfe)
return processor.normalize(dfs)
__all__ = ["parse_tim_bill_pdf", "TimBillParser", "PDFBillingProcessor"]

View File

@@ -0,0 +1,533 @@
from __future__ import annotations
import io
import re
import unicodedata as ud
from pathlib import Path
from typing import Dict, Union, Any
import pandas as pd
import pdfplumber
###############################################################################
# Normalização #
###############################################################################
_DASH_CHARS = "\u2010\u2011\u2012\u2013\u2014\u2212"
_NBSP_CHARS = "\u00A0\u202F\u2007"
_dash_trans = str.maketrans({c: "-" for c in _DASH_CHARS})
_nbsp_trans = str.maketrans({c: " " for c in _NBSP_CHARS})
def _normalize_line(s: str) -> str:
s = s.translate(_dash_trans).translate(_nbsp_trans)
s = ud.normalize("NFKC", s)
return re.sub(r"\s{2,}", " ", s.strip())
def _parse_money(value: str) -> float | None:
value = value.strip()
if value == "-":
return None
return float(value.replace(".", "").replace(",", "."))
###############################################################################
# Regex Cabeçalhos #
###############################################################################
RX_MSISDN_HEADER = re.compile(r"Vantagens que seu plano oferece:\s*(?P<msisdn>\d{2}\s\d{5}-\d{4})", re.I)
RX_MSISDN_SEU_NUM = re.compile(r"SEU\s+NÚMERO\s+TIM\s+(?P<msisdn>\d{2}\s\d{5}-\d{4})", re.I)
RX_MSISDN_DETALHE = re.compile(r"Detalhamento de Serviços\s+N[°º]\s*(?P<msisdn>\d{2}\s\d{5}-\d{4})", re.I)
SECTION_HEADERS: Dict[str, str] = {
"IGNORE Ilimitados": r"^Detalhamento de Serviços Ilimitados",
"IGNORE Detalhamento": r"^Detalhamento de Serviç[io]s\b",
"Fatura Resumo": r"^FATURA\s+RESUMO",
"DANFE-COM": r"^DANFE-COM\b",
"Plano": r"^Plano\b",
"Mensalidades Adicionais": r"^MENSALIDADES\s+ADICIONAIS",
"Itens Eventuais": r"^ITENS\s+EVENTUAIS",
"TIM Viagem": r"^TIM\s+VIAGEM",
"SVA Detalhe Total": r"^Serviços\s+de\s+Valor\s+Adicionado\s+Total",
"Desconto Franquia": r"^Desconto\(s\)\s+Franquia",
"Desconto SVA": r"^Desconto\(s\)\s+Serviç[io]s",
"Franquia": r"^Franquia\s*\(s\)",
"SVA": r"^Serviços\s+de\s+valor\s+adicionado\(SVA\)",
"Chamadas Rede TIM": r"^CHAMADAS\s+DENTRO\s+DA\s+REDE\s+TIM",
"Chamadas Fora Rede TIM": r"^CHAMADAS\s+FORA\s+DA\s+REDE\s+TIM",
"Outros Valores": r"^OUTROS\s+VALORES",
"Deduções": r"^DEDUÇÕES",
"Roaming Internacional": r"^ROAMING\s+INTERNACIONAL",
"Cobranças de Terceiros": r"^COBRANÇAS\s+DE\s+TERCEIROS",
"Débitos de outras operadoras": r"^DÉBITOS\s+DE\s+OUTRAS\s+OPERADORAS"
}
SECTION_REGEX = {k: re.compile(v, re.I) for k, v in SECTION_HEADERS.items()}
RX_SECTION_TOTAL = re.compile(r"(?:R\$\s*)?(-?[\d\.]+,\d{2})")
# Patterns que encerram a seção atual sem iniciar uma nova
RX_SECTION_BREAK = re.compile(
r"^(Nota Fiscal de Servi|SEUS\s+DADOS|ITEM\s+QTDE\s+ICMS|TOTAL\s+TIM|"
r"Ficou\s+com\s+dúvidas|Bancos\s+Conveniados|Reservado\s+ao\s+fisco|"
r"Tipo:\s+N\s+-\s+Normal)",
re.I,
)
###############################################################################
# Regex Linhas #
###############################################################################
RX_PERIOD = r"(?P<period>(?:\d{2}/\d{2}\s+a\s+\d{2}/\d{2}|-))"
RX_DAYS = r"(?P<days>(?:\d+|-))"
RX_VALUE = r"(?P<value>-?\d+,\d{2}|Incluído)"
RX_PARCEL = r"(?P<parcel>(?:\d+/\d+|-))"
# --- Plano / Desconto / Chamadas (layout padrão: QTY DESC PARCELA PERIOD DIAS VALOR) ---
RX_SIMPLE = re.compile(rf"^\s*(?P<qty>\d+)\s+(?P<desc>.+?)\s+{RX_PARCEL}\s+{RX_PERIOD}\s+{RX_DAYS}\s+{RX_VALUE}\s*$")
RX_CONSUMPTION = re.compile(rf"^\s*(?P<qty>\d+)\s+(?P<desc>.+?)\s+{RX_PARCEL}\s+(?P<franchise>Ilimitado|-)\s+(?P<consumption>\d{{1,3}}m\d{{2}}s)\s+{RX_PERIOD}\s+{RX_DAYS}\s+{RX_VALUE}\s*$")
RX_SUBTOTAL = re.compile(r"^Subtotal\s+(?P<value>-?\d+,\d{2})\s*$", re.I)
RX_DETAIL = re.compile(r"^\d+\s+.+?\s+(-?\d+,\d{2})\s*$")
# Fatura Resumo
RX_RESUMO = re.compile(r"^\s*(?P<desc>.+?)\s+R\$\s*(?P<value>-?\d+,\d{2})\s*$")
RX_TOTAL_GERAL = re.compile(r"^Total\s+geral\s+R\$\s*(?P<value>-?\d+,\d{2})", re.I)
RX_FATURA_METADATA = re.compile(
r"FATURA\s+PER[ÍI]ODO\s+EMISS[ÃA]O\s+POSTAGEM\s+"
r"(?P<fatura>\S+)\s+"
r"(?P<period>\d{2}/\d{2}\s+a\s+\d{2}/\d{2})\s+"
r"(?P<emissao>\d{2}/\d{2}/\d{4})\s+"
r"(?P<postagem>\d{2}/\d{2}/\d{4})",
re.I,
)
RX_DANFE_TOTAL = re.compile(r"^Total\s+geral\s+R\$\s*(?P<value>-?\d+(?:\.\d{3})*,\d{2})", re.I)
RX_DANFE_ROW = re.compile(
r"^(?P<desc>.+?)\s+"
r"(?P<unit>[A-Z]{2})\s+"
r"(?P<qty>\d+(?:,\d+)?)\s+"
r"(?P<preco_unit>-?\d+(?:\.\d{3})*,\d{2})\s+"
r"(?P<pis_cofins>-?\d+(?:\.\d{3})*,\d{2}|-)\s+"
r"(?P<bc_icms>-?\d+(?:\.\d{3})*,\d{2}|-)\s+"
r"(?P<aliq_icms>\d+(?:,\d+)?%|-)\s+"
r"(?P<icms>-?\d+(?:\.\d{3})*,\d{2}|-)\s+"
r"(?P<value>-?\d+(?:\.\d{3})*,\d{2})$"
)
# --- Itens Eventuais (layout: QTY DESC PARCELA FRANQUIA CONSUMO PERIODO DIAS VALOR) ---
# Com consumo real (ex: 19,77GB) ou consumo zerado ("0")
RX_EVENTUAIS = re.compile(
r"^\s*(?P<qty>\d+)\s+(?P<desc>.+?)\s+-\s+-\s+"
r"(?P<consumption>(?:\S+(?:GB|MB|KB)|0))\s+-\s+-\s+"
r"(?P<value>-?\d+,\d{2})\s*$"
)
# Sem consumo (todos "-")
RX_EVENTUAIS_NO_CONS = re.compile(
r"^\s*(?P<qty>\d+)\s+(?P<desc>.+?)"
r"(?:\s+-){5}\s+"
r"(?P<value>-?\d+,\d{2})\s*$"
)
# --- SVA Detalhe Total (layout: # DATA HORA ORIGEM DESC NUMERO TIPO PACOTE - - VALOR) ---
# Exemplo: 1 09/04/25 - 02:54:18 RJ AREA 21 TIM Saude Mensal 00700001003511 N FP - - 14,99
RX_SVA_DETAIL = re.compile(
r"^\s*(?P<seq>\d+)\s+"
r"(?P<date>\d{2}/\d{2}/\d{2})\s+-\s+(?P<time>\d{2}:\d{2}:\d{2})\s+"
r"\S+\s+AREA\s+\d{2}\s+" # origem (ex: RJ AREA 21)
r"(?P<desc>.+?)\s+"
r"(?P<number>\d{10,})\s+"
r"[A-Z/]+\s+[A-Z]+\s+"
r"-\s+-\s+"
r"(?P<value>-?\d+,\d{2})\s*$"
)
# Linha de total SVA (ex: "3 - 2 2 29,98")
RX_SVA_SUMMARY = re.compile(
r"^\s*(?P<seq>\d+)\s+-\s+\d+\s+\d+\s+(?P<value>-?\d+,\d{2})\s*$"
)
# --- Informações Complementares (layout: QTY DESC PARCELA PERÍODO DIAS VALOR) ---
RX_INFO_COMPL = re.compile(
r"^\s*(?P<qty>\d+)\s+(?P<desc>.+?)\s+"
r"(?P<parcel>(?:\d+/\d+|-))\s+"
r"(?P<period>\d{2}/\d{2}\s+a\s+\d{2}/\d{2})\s+"
r"(?P<days>\d+)\s+"
r"(?P<value>-?\d+,\d{2})\s*$"
)
# --- Chamadas resumo (layout: QTY DESC PARCELA FRANQUIA CONSUMO PERIODO DIAS VALOR) ---
RX_CHAMADAS = re.compile(
r"^\s*(?P<qty>\d+)\s+(?P<desc>.+?)\s+-\s+-\s+"
r"(?P<consumption>\d{1,3}m\d{2}s)\s+-\s+-\s+"
r"(?P<value>-?\d+,\d{2})\s*$"
)
# --- Mensalidades Adicionais (layout: QTY DESC PARCELA FRANQUIA CONSUMO PERIODO DIAS VALOR) ---
# Ex.: "1 Apple Music SVA Mes - - 0 - - 21,40" (consumo "0" e sem período)
# "1 Internet 30GB - - - 25/04 a 24/05 30 0,00"
RX_MENSALIDADE = re.compile(
rf"^\s*(?P<qty>\d+)\s+(?P<desc>.+?)\s+{RX_PARCEL}\s+"
rf"(?P<franchise>Ilimitado|-)\s+(?P<consumption>\S+)\s+"
rf"{RX_PERIOD}\s+{RX_DAYS}\s+{RX_VALUE}\s*$"
)
###############################################################################
# Parser #
###############################################################################
class TimBillParser:
"""Extrai e estrutura faturas TIM."""
def __init__(self, *, x_tolerance: float = 1.5, y_tolerance: float = 3.0):
self.x_tol = x_tolerance
self.y_tol = y_tolerance
self.data: Dict[str, pd.DataFrame] = {}
# ---------------- API pública ----------------
def parse_pdf(self, pdf_bytes: io.BytesIO) -> Dict[str, pd.DataFrame]:
# 1. Extrai texto bruto de todas as páginas
with pdfplumber.open(pdf_bytes) as pdf:
raw_text = "\n".join(
page.extract_text(x_tolerance=self.x_tol,
y_tolerance=self.y_tol) or ""
for page in pdf.pages
)
# ------------------------------------------------------------------
# 2. Captura o bloco FATURA RESUMO inteiro
bloco_pat = re.compile(
r"FATURA\s+RESUMO(?P<body>.*?)Total\s+geral\s+R\$\s*(?P<total>-?[\d\.,]+)",
re.S | re.I,
)
resumo_items = []
resumo_metadata = self._extract_fatura_metadata(raw_text)
if resumo_metadata.get("period"):
resumo_items.append(
dict(qty=None, desc="PERÍODO", parcel=None, period=resumo_metadata["period"],
days=None, value=None, franchise=None, consumption=None, msisdn=None,
emissao=None, section_total=None)
)
if resumo_metadata.get("emissao"):
resumo_items.append(
dict(qty=None, desc="EMISSÃO", parcel=None, period=None,
days=None, value=None, franchise=None, consumption=None, msisdn=None,
emissao=resumo_metadata["emissao"], section_total=None)
)
m_resumo = bloco_pat.search(raw_text)
if m_resumo:
corpo = m_resumo.group("body")
total_val = float(m_resumo.group("total").replace(".", "").replace(",", "."))
for ln in corpo.splitlines():
ln = _normalize_line(ln)
if not ln:
continue
m_ln = re.match(r"(.+?)\s+R\$\s*([-\d\.,]+)", ln)
if m_ln:
resumo_items.append(
dict(qty=None, desc=m_ln.group(1), parcel=None, period=None,
days=None,
value=float(m_ln.group(2).replace(".", "").replace(",", ".")),
franchise=None, consumption=None, msisdn=None,
section_total=None)
)
resumo_items.append(
dict(qty=None, desc="Total geral", parcel=None, period=None,
days=None, value=total_val, franchise=None, consumption=None,
msisdn=None, section_total=None)
)
# 3. Remove o bloco para que não polua a etapa linha-a-linha
raw_text = raw_text.replace(m_resumo.group(0), "")
# ------------------------------------------------------------------
# 4. Processa o restante normalmente
dfs = self._parse_text(raw_text)
if resumo_items:
dfs["Fatura Resumo"] = pd.DataFrame(resumo_items)
self.data = dfs
return dfs
# ---------------- interno -------------------
def _extract_fatura_metadata(self, text: str) -> dict[str, str]:
normalized_lines = [_normalize_line(line) for line in text.splitlines()]
normalized_text = " ".join(line for line in normalized_lines if line)
if m := RX_FATURA_METADATA.search(normalized_text):
return {
"period": m.group("period"),
"emissao": m.group("emissao"),
}
return {}
def _parse_text(self, text: str) -> Dict[str, pd.DataFrame]:
"""Quebra o texto extraído em DataFrames por seção."""
buf: Dict[str, list] = {k: [] for k in SECTION_HEADERS if not k.startswith("IGNORE")}
current_sec = current_msisdn = None
current_total: float | None = None
last_sva_detail_item: dict | None = None
for raw in text.splitlines():
line = _normalize_line(raw)
if not line:
continue
# cabeçalho de MSISDN (3 variantes)
for rx_ms in (RX_MSISDN_HEADER, RX_MSISDN_SEU_NUM, RX_MSISDN_DETALHE):
if (m := rx_ms.search(line)):
current_msisdn = m.group("msisdn").replace(" ", "")
break
else:
m = None
if m:
continue
# section break — encerra seção atual sem iniciar outra
if RX_SECTION_BREAK.match(line):
current_sec = None
continue
# detecta novo cabeçalho (a menos que estejamos em Fatura Resumo)
if current_sec != "Fatura Resumo":
sec = next((s for s, rx in SECTION_REGEX.items() if rx.match(line)), None)
else:
sec = None
if (sec in ("IGNORE Ilimitados", "IGNORE Detalhamento")):
current_sec = None
continue
if sec is not None:
current_sec = sec
last_sva_detail_item = None
mt = RX_SECTION_TOTAL.search(line)
current_total = float(mt.group(1).replace(".", "").replace(",", ".")) if mt else None
continue
if not current_sec:
if line[0].isdigit():
item = self._parse_sva_detail(line)
if item:
current_sec = "SVA Detalhe Total"
current_total = None
item["msisdn"] = current_msisdn
item["section_total"] = None
buf.setdefault(current_sec, []).append(item)
last_sva_detail_item = item
continue
# pula cabeçalhos de página
if re.match(r"^Página\s+\d+\s+de\s+\d+", line, re.I):
continue
if current_sec == "DANFE-COM":
item = self._parse_danfe(line)
if item:
item["msisdn"] = None
item["section_total"] = current_total
buf.setdefault(current_sec, []).append(item)
if item.get("is_total"):
current_sec = None
continue
if current_sec == "SVA Detalhe Total":
if self._is_sva_header_line(line):
continue
if RX_SVA_SUMMARY.match(line):
last_sva_detail_item = None
continue
if line[0].isdigit():
item = self._parse_sva_detail(line)
if item:
item["msisdn"] = current_msisdn
item["section_total"] = current_total
buf.setdefault(current_sec, []).append(item)
last_sva_detail_item = item
continue
if last_sva_detail_item:
last_sva_detail_item["desc"] = (
f"{last_sva_detail_item['desc']} {line}"
).strip()
continue
# -------- linhas padrão --------
if not (line[0].isdigit() or line.lower().startswith("subtotal")):
continue
item = self._parse_item_line(line, current_sec)
if item:
item["msisdn"] = current_msisdn
item["section_total"] = current_total
buf.setdefault(current_sec, []).append(item)
return {s: pd.DataFrame(lst) for s, lst in buf.items() if lst}
# ------------------------------------------------------------------
def _parse_item_line(self, line: str, section: str = "") -> dict | None:
"""Parseia uma linha de item de acordo com a seção."""
# Ignora subtotal
if RX_SUBTOTAL.match(line):
return None
# ── Mensalidades Adicionais ──
if section == "Mensalidades Adicionais":
return self._parse_mensalidades(line)
# ── Itens Eventuais ──
if section == "Itens Eventuais":
return self._parse_eventuais(line)
# ── SVA Detalhe Total ──
if section == "SVA Detalhe Total":
return self._parse_sva_detail(line)
# ── DANFE-COM ──
if section == "DANFE-COM":
return self._parse_danfe(line)
# ── Chamadas Rede TIM / Chamadas Fora Rede TIM ──
if section.startswith("Chamadas"):
return self._parse_chamadas(line)
# ── Plano / Franquia / SVA / Desconto Franquia / Desconto SVA (layout padrão) ──
return self._parse_standard(line)
# ------------------------------------------------------------------
def _parse_danfe(self, line: str) -> dict | None:
"""DANFE-COM: linhas da tabela de itens e total geral."""
if line.upper().startswith("ITENS "):
return None
if (m := RX_DANFE_TOTAL.match(line)):
return {
"desc": "Total geral",
"unit": None,
"qty": None,
"preco_unit": None,
"pis_cofins": None,
"bc_icms": None,
"aliq_icms": None,
"icms": None,
"value": _parse_money(m.group("value")),
"is_total": True,
}
if (m := RX_DANFE_ROW.match(line)):
d = m.groupdict()
return {
"desc": d["desc"].strip(),
"unit": d["unit"],
"qty": float(d["qty"].replace(",", ".")),
"preco_unit": _parse_money(d["preco_unit"]),
"pis_cofins": _parse_money(d["pis_cofins"]),
"bc_icms": _parse_money(d["bc_icms"]),
"aliq_icms": None if d["aliq_icms"] == "-" else d["aliq_icms"],
"icms": _parse_money(d["icms"]),
"value": _parse_money(d["value"]),
"is_total": False,
}
return None
# ------------------------------------------------------------------
def _parse_standard(self, line: str) -> dict | None:
"""Regex padrão: QTY DESC PARCELA [FRANCHISE CONSUMPTION] PERIOD DAYS VALUE."""
for rx in (RX_CONSUMPTION, RX_SIMPLE):
if (m := rx.match(line)):
d = m.groupdict()
# --- corrige parcel dentro de desc (caso d["parcel"] == "-") ----
if d["parcel"] == "-":
tail = re.search(r"\b(\d+/\d+)$", d["desc"])
if tail:
d["parcel"] = tail.group(1)
d["desc"] = d["desc"][: tail.start()].rstrip(" -")
# ----------------------------------------------------------------
# limpa trailing dashes e valores de franquia residuais do desc
d["desc"] = re.sub(r"(\s+-\s+\d+(?:GB|MB|KB))(?:\s+-)*\s*$|(?:\s+-)+\s*$", "", d["desc"]).strip()
value = d["value"]
d["qty"] = float(d["qty"])
d["days"] = None if d.get("days") in (None, "-") else int(d["days"])
d["_is_included_value"] = value == "Incluído"
d["value"] = 0.0 if d["_is_included_value"] else float(value.replace(",", "."))
return d
return None
# ------------------------------------------------------------------
def _parse_eventuais(self, line: str) -> dict | None:
"""Itens Eventuais: QTY DESC PARCELA FRANQUIA CONSUMO PERIODO DIAS VALUE."""
# Tenta com consumo real (ex: 19,77GB)
if (m := RX_EVENTUAIS.match(line)):
return {
"qty": float(m.group("qty")),
"desc": m.group("desc").strip(),
"parcel": None,
"period": None,
"days": None,
"value": float(m.group("value").replace(",", ".")),
"franchise": None,
"consumption": None if m.group("consumption") == "0" else m.group("consumption"),
}
# Tenta sem consumo (todos "-")
if (m := RX_EVENTUAIS_NO_CONS.match(line)):
return {
"qty": float(m.group("qty")),
"desc": m.group("desc").strip(),
"parcel": None,
"period": None,
"days": None,
"value": float(m.group("value").replace(",", ".")),
"franchise": None,
"consumption": None,
}
return None
# ------------------------------------------------------------------
def _parse_mensalidades(self, line: str) -> dict | None:
"""Mensalidades Adicionais: QTY DESC PARCELA FRANQUIA CONSUMO PERIODO DIAS VALOR."""
if (m := RX_MENSALIDADE.match(line)):
d = m.groupdict()
d["qty"] = float(d["qty"])
d["desc"] = d["desc"].strip()
d["parcel"] = None if d["parcel"] == "-" else d["parcel"]
d["franchise"] = None if d["franchise"] == "-" else d["franchise"]
d["consumption"] = None if d["consumption"] in ("-", "0") else d["consumption"]
d["period"] = None if d["period"] == "-" else d["period"]
d["days"] = None if d["days"] == "-" else int(d["days"])
value = d["value"]
d["_is_included_value"] = value == "Incluído"
d["value"] = 0.0 if d["_is_included_value"] else float(value.replace(",", "."))
return d
# Layout de 6 colunas (sem franquia/consumo) → regex padrão
return self._parse_standard(line)
# ------------------------------------------------------------------
def _is_sva_header_line(self, line: str) -> bool:
return bool(
re.match(r"^(DURAÇÃO/VOLUME|#\s+DATA\s*/\s*HORA)\b", line, re.I)
)
# ------------------------------------------------------------------
def _parse_sva_detail(self, line: str) -> dict | None:
"""SVA Detalhe Total: linhas com data/hora e linha de totalização."""
# Linha de detalhe com data/hora
if (m := RX_SVA_DETAIL.match(line)):
return {
"qty": 1.0,
"desc": m.group("desc").strip(),
"parcel": None,
"period": m.group("date"),
"days": None,
"value": float(m.group("value").replace(",", ".")),
"franchise": None,
"consumption": None,
}
return None
# ------------------------------------------------------------------
def _parse_chamadas(self, line: str) -> dict | None:
"""Chamadas Rede TIM / Fora Rede: QTY DESC - - CONSUMPTION - - VALUE."""
if (m := RX_CHAMADAS.match(line)):
return {
"qty": float(m.group("qty")),
"desc": m.group("desc").strip(),
"parcel": None,
"period": None,
"days": None,
"value": float(m.group("value").replace(",", ".")),
"franchise": None,
"consumption": m.group("consumption"),
}
# Fallback para o padrão (algumas chamadas usam formato padrão)
return self._parse_standard(line)

View File

@@ -0,0 +1,743 @@
from __future__ import annotations
import re
import unicodedata as ud
from typing import Any, Dict, List, Tuple
import pandas as pd
# ---------------------------------------------------------------------------
# Regex para linha de VAS
# ---------------------------------------------------------------------------
RX_VAS_LINE = re.compile(
r"""
^\d+\s+ # índice "#"
(?P<date>\d{2}/\d{2}/\d{2}) # DD/MM/YY
\s+-\s+\d{2}:\d{2}:\d{2}\s+ # " - HH:MM:SS "
[A-Z]{2}\sAREA\s\d+\s+ # "SP AREA 11"
(?P<name>.+?)\s+ # nome do serviço
\d{8,} # número chamado
""",
re.X,
)
# ---------------------------------------------------------------------------
class PDFBillingProcessor:
"""
Pós-processamento dos DataFrames gerados pelo TimBillParser.
"""
SECTIONS = [
"Fatura Resumo",
"Plano",
"DANFE-COM",
"Descontos",
"Itens Eventuais",
"Mensalidades Adicionais",
"TIM Viagem",
"Outros Valores",
"Chamadas Rede TIM",
"SVA Detalhe Total",
"Serviços Bundle Inclusos",
"Deduções",
"Roaming Internacional",
"Cobranças de Terceiros",
"Débitos de outras operadoras",
]
STRATEGIC_SERVICE_SECTIONS = {
"SVA Detalhe Total",
"Itens Eventuais",
"Serviços Bundle Inclusos",
"Mensalidades Adicionais",
"Outros Valores",
"Cobranças de Terceiros",
}
SECTION_CLASS_MAP = {
"SVA Detalhe Total": "avulso",
"Itens Eventuais": "avulso",
"Serviços Bundle Inclusos": "bundle",
}
CLASSE_VERB_MAP = {
"avulso": "cancelar",
"bundle": "falar sobre",
"estrategico": "falar sobre",
}
STRATEGIC_SERVICES = [
"Apple Music",
"Deezer",
"Disney",
"Fuze",
"Forge",
"HBO",
"Looke",
"Max Mensal",
"Netflix",
"Paramount",
"TIM Cloud Gaming",
"YouTube",
"Globoplay",
"Amazon Prime"
]
DIGIT_WORDS = {
"0": "zero",
"1": "um",
"2": "dois",
"3": "tres",
"4": "quatro",
"5": "cinco",
"6": "seis",
"7": "sete",
"8": "oito",
"9": "nove",
}
def __init__(self, *, include_danfe: bool = False):
self.include_danfe = include_danfe
self._strategic_service_patterns = [
re.compile(rf"(?:^|\s){re.escape(self._service_match_key(service))}(?:\s|$)")
for service in self.STRATEGIC_SERVICES
]
def remove_parentheses(self, text: str) -> str:
return re.sub(r'\s*\([^)]*\)', '', str(text)).strip()
def remove_plan_recognition_marker(self, text: str) -> str:
return re.sub(
r"\s*\(\s*\d+\s*/\s*P[ÓO]S\s*/\s*SMP\s*\)",
"",
str(text),
flags=re.I,
).strip()
def _format_plan_version_number(self, text: str) -> str:
return re.sub(r"(?<!\d)(\d)\s+(\d)(?!\d)", r"\1.\2", str(text))
def _format_msisdn(self, text: Any) -> str:
return re.sub(r"\D", "", str(text))
def _vocalize_digits(self, digits: str) -> str:
return " ".join(self.DIGIT_WORDS[d] for d in digits if d in self.DIGIT_WORDS)
def _collect_msisdns(self, node: Any, found: set) -> None:
"""Percorre recursivamente o payload coletando todos os msisdn presentes."""
if isinstance(node, dict):
for key, value in node.items():
if key == "msisdn" and value is not None:
msisdn = self._format_msisdn(value)
if msisdn:
found.add(msisdn)
else:
self._collect_msisdns(value, found)
elif isinstance(node, list):
for item in node:
self._collect_msisdns(item, found)
def _build_vocalized_msisdn(self, final_output: Dict[str, Any]) -> Dict[str, str]:
"""Mapeia cada msisdn da fatura para a vocalização dos seus 4 últimos dígitos."""
found: set = set()
for key, value in final_output.items():
if re.fullmatch(r"\d+", str(key)):
found.add(self._format_msisdn(key))
self._collect_msisdns(value, found)
return {
msisdn: self._vocalize_digits(msisdn[-4:])
for msisdn in sorted(found)
}
def _clean_plan_name(self, desc: str, *, format_version_number: bool = True) -> str:
text = self.remove_parentheses(self.remove_plan_recognition_marker(desc))
if format_version_number:
text = self._format_plan_version_number(text)
return text
def _discount_match_key(self, desc: str) -> str:
text = self._clean_plan_name(desc)
text = ud.normalize("NFKD", text)
text = "".join(ch for ch in text if not ud.combining(ch))
text = text.casefold()
text = re.sub(r"\b\d+/\d+\b", " ", text)
text = re.sub(r"\b\d+\b", " ", text)
text = re.sub(r"[^a-z]+", " ", text)
return re.sub(r"\s+", " ", text).strip()
def _service_match_key(self, desc: str) -> str:
text = ud.normalize("NFKD", str(desc))
text = "".join(ch for ch in text if not ud.combining(ch))
text = text.casefold()
text = re.sub(r"[^a-z0-9]+", " ", text)
return re.sub(r"\s+", " ", text).strip()
def _is_strategic_service(self, desc: Any) -> bool:
desc_key = self._service_match_key(str(desc or ""))
return any(pattern.search(desc_key) for pattern in self._strategic_service_patterns)
def _is_controle_plan(self, desc: Any) -> bool:
desc_key = self._service_match_key(str(desc or ""))
return bool(re.search(r"\b(?:controle|ctrl|crtl)\b", desc_key))
def calculate_discount(self, desc_match: str, msisdn: str, descontos_df: pd.DataFrame) -> float:
# Filtra por msisdn e verifica se o desc_match está contido no desc
descontos_filtrados = descontos_df[
(descontos_df['msisdn'] == msisdn) &
(descontos_df['desc'].str.lower().str.contains(desc_match.lower(), na=False))
]
return descontos_filtrados['value'].sum()
# ------------------------------------------------------------------
def normalize(self, raw: Dict[str, pd.DataFrame]) -> Dict[str, Any]:
all_msisdns = set()
for sec, df in raw.items():
if sec != "Fatura Resumo" and "msisdn" in df.columns:
all_msisdns.update(df["msisdn"].dropna().astype(str).unique())
final_output: Dict[str, Any] = {}
# Processa Fatura Resumo primeiro (independente de MSISDN)
if "Fatura Resumo" in raw:
fatura_raw = {"Fatura Resumo": raw["Fatura Resumo"]}
fatura_dfs = self._clean_dataframes(fatura_raw)
fatura_json = self._build_final_json(fatura_dfs)
if "Fatura Resumo" in fatura_json:
final_output["Fatura Resumo"] = fatura_json["Fatura Resumo"]
if self.include_danfe and "DANFE-COM" in raw:
danfe_json = self._build_danfe_payload(raw["DANFE-COM"], raw)
if danfe_json:
final_output["DANFE-COM"] = danfe_json
if not all_msisdns:
# Se não houver MSISDNs, processa tudo como global
dfs = self._clean_dataframes(raw)
dfs = self._process_plano(dfs)
dfs = self._process_eventuais(dfs)
dfs = self._process_vas(dfs)
dfs = self._process_descontos(dfs)
fallback_json = self._build_final_json(dfs)
for k, v in fallback_json.items():
if k not in final_output:
final_output[k] = v
final_output["vocalized_msisdn"] = self._build_vocalized_msisdn(final_output)
return final_output
for msisdn in all_msisdns:
msisdn_raw = {}
for sec, df in raw.items():
if sec == "Fatura Resumo":
continue
if "msisdn" in df.columns:
mask = df["msisdn"].astype(str) == msisdn
filtered_df = df[mask].copy()
if not filtered_df.empty:
msisdn_raw[sec] = filtered_df
else:
# Seções sem MSISDN podem ser globais? (Ex: Fatura Resumo já tratada)
pass
if msisdn_raw:
dfs = self._clean_dataframes(msisdn_raw)
dfs = self._process_plano(dfs)
dfs = self._process_eventuais(dfs)
dfs = self._process_vas(dfs)
dfs = self._process_descontos(dfs)
msisdn_json = self._build_final_json(dfs)
if msisdn_json:
final_output[self._format_msisdn(msisdn)] = msisdn_json
final_output["vocalized_msisdn"] = self._build_vocalized_msisdn(final_output)
return final_output
def _clean_dataframes(self, raw: Dict[str, pd.DataFrame]) -> Dict[str, pd.DataFrame]:
# 1) remove value == 0 exceto de fatura resumo e plano (que pode ter o bundle)
dfs = {
sec: (df if sec in ["Fatura Resumo", "Plano"] else df[df.value != 0.0]).copy()
for sec, df in raw.items() if "value" in df.columns
}
# 2) drop colunas totalmente NaN
dfs = {
sec: df.dropna(axis=1, how="all")
for sec, df in dfs.items() if not df.dropna(axis=1, how="all").empty
}
# 3) remove sufixo " - -" do campo desc
for df in dfs.values():
if "desc" in df.columns:
df["desc"] = df["desc"].str.replace(r"\s*- -\s*$", "", regex=True)
df["desc"] = df["desc"].str.strip()
return dfs
def _process_plano(self, dfs: Dict[str, pd.DataFrame]) -> Dict[str, pd.DataFrame]:
if "Plano" not in dfs:
return dfs
plano_df = dfs["Plano"]
if 'msisdn' in plano_df.columns:
plano_df['msisdn'] = plano_df['msisdn'].astype(str)
# Separa somente itens que vieram textualmente como "Incluído".
# Planos dependentes podem aparecer como R$ 0,00 e continuam sendo Plano.
if "_is_included_value" in plano_df.columns:
included_mask = plano_df["_is_included_value"].fillna(False).astype(bool)
else:
included_mask = plano_df.value == 0.0
bundle_df = plano_df[included_mask].copy()
plano_df = plano_df[~included_mask].copy()
if not bundle_df.empty:
bundle_df["value"] = "Incluído"
if "section_total" in bundle_df.columns:
bundle_df = bundle_df.drop(columns=["section_total"])
dfs["Serviços Bundle Inclusos"] = bundle_df
# Seleciona planos principais
mask_plan = plano_df["desc"].str.contains(r"PÓS/SMP", case=False, na=False)
if mask_plan.sum() == 0:
mask_plan = plano_df["desc"].str.match(r"(?i)^tim", case=False)
# Seleciona descontos
descontos_df = plano_df[plano_df['desc'].apply(lambda x: 'desc' in str(x).lower() and 'tim' in str(x).lower())]
plano_df = plano_df[mask_plan].copy()
plano_df["desc"] = plano_df["desc"].apply(self.remove_plan_recognition_marker)
dfs["_descontos_temp"] = descontos_df
if plano_df.empty:
dfs.pop("Plano", None)
else:
dfs["Plano"] = plano_df
return dfs
def _process_eventuais(self, dfs: Dict[str, pd.DataFrame]) -> Dict[str, pd.DataFrame]:
if "Itens Eventuais" in dfs:
ie_df = dfs["Itens Eventuais"]
mask_remove = (ie_df["value"] == 0) | (ie_df["desc"].str.contains("Serviços de Valor Adicionado Conteúdo", case=False, na=False))
ie_df = ie_df[~mask_remove].copy()
if ie_df.empty:
dfs.pop("Itens Eventuais")
else:
dfs["Itens Eventuais"] = ie_df
return dfs
def _process_vas(self, dfs: Dict[str, pd.DataFrame]) -> Dict[str, pd.DataFrame]:
"""Remove de 'Mensalidades Adicionais' os serviços recorrentes que já vêm
detalhados (com data de ativação) em 'SVA Detalhe Total', evitando duplicata.
A seção 'Serviços de Valor Adicionado Total' do PDF é o detalhamento que
reúne tanto os itens eventuais quanto as mensalidades recorrentes; quando o
mesmo serviço aparece nas duas seções, mantemos a cópia detalhada do SVA."""
sva_df = dfs.get("SVA Detalhe Total")
if sva_df is None or sva_df.empty or "desc" not in sva_df.columns:
return dfs
detalhados = {
(self._format_msisdn(rec.get("msisdn")), self._service_match_key(rec.get("desc")))
for rec in sva_df.to_dict(orient="records")
}
for section in ("Mensalidades Adicionais", "Itens Eventuais"):
df = dfs.get(section)
if df is None or df.empty or "desc" not in df.columns:
continue
mask_dup = df.apply(
lambda r: (
self._format_msisdn(r.get("msisdn")),
self._service_match_key(r.get("desc")),
) in detalhados,
axis=1,
)
if mask_dup.any():
df = df[~mask_dup].copy()
if df.empty:
dfs.pop(section, None)
else:
dfs[section] = df
return dfs
def _process_descontos(self, dfs: Dict[str, pd.DataFrame]) -> Dict[str, pd.DataFrame]:
if "_descontos_temp" in dfs:
descontos_df = dfs.pop("_descontos_temp")
if not descontos_df.empty:
if "section_total" in descontos_df.columns:
descontos_df = descontos_df.drop(columns=["section_total"])
descontos_df['installment'] = descontos_df['desc'].str.extract(r'(\d+/\d+)')
descontos_df['desc'] = descontos_df['desc'].apply(self._format_plan_version_number)
if "Descontos" in dfs and not dfs["Descontos"].empty:
dfs["Descontos"] = pd.concat(
[dfs["Descontos"], descontos_df],
ignore_index=True,
)
else:
dfs["Descontos"] = descontos_df
return dfs
def _clean_record(self, rec: Dict[str, Any]) -> Dict[str, Any]:
redundant_values = {
"qty": [1.0, 1],
"parcel": ["-", None],
"franchise": [None, "null", "-"],
"consumption": [None, "null"],
"period": ["-", None],
"value": [None],
"emissao": [None, "null", "-"],
}
cleaned_rec = {}
for k, v in rec.items():
if k == "section_total" or k.startswith("_"):
continue
if k == "msisdn":
v = self._format_msisdn(v)
if pd.isna(v):
v = None
elif k == "value" and isinstance(v, (int, float)):
v = self._round_money(v)
elif k == "days" and isinstance(v, float) and v.is_integer():
v = int(v)
if k in redundant_values and v in redundant_values[k]:
continue
cleaned_rec[k] = v
return cleaned_rec
def _records_for_section(self, df: pd.DataFrame) -> List[Dict[str, Any]]:
return [
self._clean_record(rec)
for rec in df.to_dict(orient="records")
]
def _split_strategic_records(
self,
df: pd.DataFrame,
section: str,
) -> Tuple[List[Dict[str, Any]], List[Dict[str, Any]]]:
records = self._records_for_section(df)
if section not in self.STRATEGIC_SERVICE_SECTIONS:
return records, []
regular_records = []
strategic_records = []
for record in records:
if "desc" in record and self._is_strategic_service(record["desc"]):
record["estrategico"] = True
strategic_records.append(record)
else:
regular_records.append(record)
return regular_records, strategic_records
def _annotate_class(
self,
records: List[Dict[str, Any]],
section: str,
) -> List[Dict[str, Any]]:
section_classe = self.SECTION_CLASS_MAP.get(section)
if not section_classe:
return records
for rec in records:
# Itens estratégicos dobrados nesta seção (commit 7fc38a4e) não
# herdam a classe da seção (avulso): mantêm classe=estrategico e
# verbo "falar sobre". Os demais seguem o default da seção.
classe = "estrategico" if rec.get("estrategico") is True else section_classe
rec["classe"] = classe
verb = self.CLASSE_VERB_MAP.get(classe)
if verb:
rec["verb"] = verb
return records
def _round_money(self, value: float) -> float:
return round(float(value) + 0.0, 2)
def _is_discount_desc(self, desc: str) -> bool:
return bool(re.match(r"(?i)^\s*desc(?:onto)?\b", desc))
def _danfe_record(self, rec: Dict[str, Any]) -> Dict[str, Any]:
cleaned = {}
for k, v in rec.items():
if k in {"section_total", "msisdn", "is_total"}:
continue
if pd.isna(v):
v = None
elif k in {"preco_unit", "pis_cofins", "bc_icms", "icms", "value"} and isinstance(v, (int, float)):
v = self._round_money(v)
elif k == "qty" and isinstance(v, float) and v.is_integer():
v = int(v)
cleaned[k] = v
return cleaned
def _danfe_item_payload(self, rec: Dict[str, Any]) -> Dict[str, Any]:
item = self._danfe_record(rec)
valor_bruto = self._round_money(item.pop("value", 0.0) or 0.0)
item["valor_bruto"] = valor_bruto
item["total_descontos"] = 0.0
item["valor_final"] = valor_bruto
item["descontos"] = []
return item
def _danfe_discount_payload(self, rec: Dict[str, Any]) -> Dict[str, Any]:
discount = self._danfe_record(rec)
if "value" in discount and discount["value"] is not None:
discount["value"] = self._round_money(discount["value"])
return discount
def _desc_matches_key(self, desc_key: str, target_key: str) -> bool:
return bool(
desc_key
and target_key
and (desc_key == target_key or desc_key.startswith(target_key) or target_key.startswith(desc_key))
)
def _discount_matches_item(self, discount_desc: str, item_desc: str) -> bool:
discount_key = self._discount_match_key(discount_desc)
item_key = self._discount_match_key(item_desc)
return bool(item_key and item_key in discount_key)
def _build_danfe_payload(
self,
danfe_df: pd.DataFrame,
raw: Dict[str, pd.DataFrame],
) -> Dict[str, Any]:
if danfe_df.empty:
return {}
total_geral = None
item_records = []
for rec in danfe_df.to_dict(orient="records"):
if bool(rec.get("is_total")):
total_geral = self._round_money(rec.get("value", 0.0) or 0.0)
else:
item_records.append(rec)
plan_names: List[str] = []
if "Plano" in raw and "desc" in raw["Plano"].columns:
plano_df = raw["Plano"]
mask_plan = plano_df["desc"].str.contains(r"PÓS/SMP", case=False, na=False)
if mask_plan.sum() == 0:
mask_plan = plano_df["desc"].str.match(r"(?i)^tim", na=False)
for desc in plano_df.loc[mask_plan, "desc"].dropna().astype(str):
plan_name = self._clean_plan_name(desc, format_version_number=False)
if plan_name not in plan_names:
plan_names.append(plan_name)
if not plan_names:
for rec in item_records:
desc = str(rec.get("desc", ""))
desc_key = self._discount_match_key(desc)
if desc_key.startswith("tim ") and not self._is_discount_desc(desc):
plan_name = self._clean_plan_name(desc, format_version_number=False)
if plan_name.casefold() != "tim music" and plan_name not in plan_names:
plan_names.append(plan_name)
plan_matchers = [(name, self._discount_match_key(name)) for name in plan_names]
other_keys: List[str] = []
if "Outros Valores" in raw and "desc" in raw["Outros Valores"].columns:
for desc in raw["Outros Valores"]["desc"].dropna().astype(str):
key = self._discount_match_key(desc)
if key and key not in other_keys:
other_keys.append(key)
payload: Dict[str, Any] = {"Planos": {name: [] for name in plan_names}}
if total_geral is not None:
payload["total_geral"] = total_geral
outros_itens: List[Dict[str, Any]] = []
current_plan: str | None = None
last_item_by_plan: Dict[str, Dict[str, Any]] = {}
for rec in item_records:
desc = str(rec.get("desc", ""))
desc_key = self._discount_match_key(desc)
matched_plan = next(
(
name
for name, plan_key in plan_matchers
if self._desc_matches_key(desc_key, plan_key)
),
None,
)
is_known_other = any(
self._desc_matches_key(desc_key, other_key)
for other_key in other_keys
)
is_discount = self._is_discount_desc(desc)
if matched_plan and not is_discount:
current_plan = matched_plan
item = self._danfe_item_payload(rec)
payload["Planos"].setdefault(current_plan, []).append(item)
last_item_by_plan[current_plan] = item
continue
if is_known_other and not is_discount:
outros_itens.append(self._danfe_item_payload(rec))
continue
if is_discount:
target_item = None
if current_plan:
for item in reversed(payload["Planos"].get(current_plan, [])):
if self._discount_matches_item(desc, str(item.get("desc", ""))):
target_item = item
break
if target_item is None:
target_item = last_item_by_plan.get(current_plan)
if target_item is None:
outros_itens.append(self._danfe_discount_payload(rec))
continue
discount = self._danfe_discount_payload(rec)
target_item["descontos"].append(discount)
continue
if current_plan:
item = self._danfe_item_payload(rec)
payload["Planos"].setdefault(current_plan, []).append(item)
last_item_by_plan[current_plan] = item
else:
outros_itens.append(self._danfe_item_payload(rec))
for items in payload["Planos"].values():
for item in items:
item["descontos"].sort(
key=lambda discount: abs(float(discount.get("value") or 0.0)),
reverse=True,
)
total_descontos = sum(
float(discount.get("value") or 0.0)
for discount in item["descontos"]
)
item["total_descontos"] = self._round_money(total_descontos)
item["valor_final"] = self._round_money(
float(item.get("valor_bruto") or 0.0) + total_descontos
)
if outros_itens:
payload["Outros Itens"] = outros_itens
return payload
def _match_discount_to_plan(
self,
discount: Dict[str, Any],
plans: List[Tuple[str, Dict[str, Any], str]],
) -> str | None:
discount_key = self._discount_match_key(str(discount.get("desc", "")))
matches = [
(plan_name, plan)
for plan_name, plan, plan_key in plans
if plan_key and plan_key in discount_key
]
if not matches:
return None
discount_period = discount.get("period")
if discount_period:
for plan_name, plan in matches:
if plan.get("period") == discount_period:
return plan_name
return matches[0][0]
def _build_plan_payload(
self,
plano_df: pd.DataFrame | None,
descontos_df: pd.DataFrame | None,
) -> tuple[Dict[str, Dict[str, Any]], List[Dict[str, Any]]]:
if plano_df is None or plano_df.empty:
return {}, self._records_for_section(descontos_df) if descontos_df is not None else []
plan_records = self._records_for_section(plano_df)
discount_records = self._records_for_section(descontos_df) if descontos_df is not None else []
payload: Dict[str, Dict[str, Any]] = {}
plan_matchers: List[Tuple[str, Dict[str, Any], str]] = []
for plan in plan_records:
desc = plan.get("desc")
if not desc:
continue
plan_name = self._clean_plan_name(str(desc))
plan_payload = {}
for field in ("period", "days", "msisdn"):
if field in plan:
plan_payload[field] = plan[field]
valor_bruto = self._round_money(plan.get("value", 0.0))
plan_payload["valor_final"] = valor_bruto
for field, value in plan.items():
if field not in {"desc", "period", "days", "msisdn", "value"}:
plan_payload[field] = value
if self._is_controle_plan(desc):
plan_payload["is_controle"] = True
plan_payload["descontos"] = []
plan_payload["total_descontos"] = 0.0
plan_payload["valor_bruto"] = valor_bruto
payload[plan_name] = plan_payload
plan_matchers.append((plan_name, plan, self._discount_match_key(plan_name)))
unmatched_discounts: List[Dict[str, Any]] = []
for discount in discount_records:
plan_name = self._match_discount_to_plan(discount, plan_matchers)
if plan_name is None:
unmatched_discounts.append(discount)
continue
discount_payload = {
"desc": discount.get("desc"),
"value": discount.get("value"),
"installment": discount.get("installment"),
}
payload[plan_name]["descontos"].append(discount_payload)
for plan in payload.values():
total_descontos = sum(
float(discount.get("value") or 0.0)
for discount in plan["descontos"]
)
plan["total_descontos"] = self._round_money(total_descontos)
valor_final = self._round_money(
float(plan.get("valor_bruto") or 0.0) + total_descontos
)
plan["valor_final"] = valor_final
return payload, unmatched_discounts
def _build_final_json(self, dfs: Dict[str, pd.DataFrame]) -> Dict[str, Any]:
out: Dict[str, Any] = {}
plano_payload, descontos_restantes = self._build_plan_payload(
dfs.get("Plano"),
dfs.get("Descontos"),
)
for sec in self.SECTIONS:
if sec == "DANFE-COM":
continue
if sec == "Plano" and plano_payload:
out["Planos"] = plano_payload
continue
if sec == "Descontos" and plano_payload:
if descontos_restantes:
out[sec] = descontos_restantes
continue
if sec in dfs:
section_records, strategic_records = self._split_strategic_records(
dfs[sec],
sec,
)
all_records = section_records + strategic_records
if all_records:
out[sec] = self._annotate_class(all_records, sec)
return out

View File

@@ -0,0 +1,305 @@
#!/usr/bin/env python3
"""Transformacao da fatura normalizada (dict JSON) -> formato textual em blocos.
Formato economico em tokens (~72% menor que o JSON indentado), pensado para enviar
a uma LLM. API publica: `to_text(data)` e a flag `USE_TEXT_FORMAT`.
"""
from __future__ import annotations
import json
import logging
import os
import re
from typing import Any
logger = logging.getLogger(__name__)
# Liga o formato textual da fatura no prompt. Default conceitual: False;
# mantido True nesta fase de rollout. Override por env, sem edicao de codigo.
USE_TEXT_FORMAT = os.getenv("TIM_INVOICE_DETAIL_AS_TEXT", "true").lower() == "true"
# ---------------------------------------------------------------------------
# secao -> (acao, classe). O cabecalho usa o proprio nome da secao (mantido como no JSON).
SEC_META = {
"SVA Detalhe Total": ("cancelar", "avulso"),
"Itens Eventuais": ("cancelar", "avulso"),
"Serviços Bundle Inclusos": ("falar sobre", "bundle"),
}
# Secoes que rendem a acao por ITEM (sem "| ação=... | classe" no header).
# Item estrategico (estrategico=True) usa "falar sobre"; avulso, "cancelar".
PER_ITEM_ACTION_SECTIONS = {
"SVA Detalhe Total",
"Itens Eventuais",
"Mensalidades Adicionais",
}
# Secoes cujo header recebe o rotulo "| cobrados a parte" (servicos avulsos
# contratados separadamente). A acao continua por item.
COBRADOS_A_PARTE_SECTIONS = {"SVA Detalhe Total", "Itens Eventuais"}
# secao do JSON -> rotulo no cabecalho do prompt. "SVA Detalhe Total" e "Itens
# Eventuais" sao a MESMA categoria (avulsos cobrados a parte) e saem sob um unico
# cabecalho "Itens Eventuais". "Serviços Bundle Inclusos" vira "Serviços Inclusos
# no Plano": a palavra "bundle" e tecnica/interna e nao deve chegar ao prompt (nem
# ao LLM). As chaves do JSON normalizado NAO mudam nos dois casos.
SECTION_LABELS = {
"SVA Detalhe Total": "Itens Eventuais",
"Serviços Bundle Inclusos": "Benefícios do Plano",
}
# classe interna -> rotulo exibido no cabecalho (ver SEC_META). Mesma logica do
# SECTION_LABELS: so a APRESENTACAO muda, a classe interna ("bundle") segue igual
# em todo o resto do backend (bill_processor, invoice_resolver, tools, etc.).
CLASSE_LABELS = {"bundle": "incluso"}
_RX_OUTROS = re.compile(r"^\s*([^:()]+?)\s*:\s*\((.+)\)\s*$")
def _fmt_money(value: Any) -> str:
if isinstance(value, (int, float)):
return f"{value:.2f}"
return str(value)
def _snake(desc: Any) -> str:
return re.sub(r"\s+", "_", str(desc).strip().lower())
def is_period_range(period: Any) -> bool:
"""True quando ``period`` é uma FAIXA (ciclo da fatura, ex.: "14/10 a 13/11"),
não uma data única de cobrança. Compartilhado com o resolver, que usa o mesmo
critério para decidir se uma entry expõe ``charge_date`` (data única) — assim o
que o resolver enxerga como cobrança datada casa exatamente o ``data=`` do render
lean do classificador."""
text = str(period)
return " a " in text or "~" in text
def _item_acao(item: dict[str, Any], section: str) -> str | None:
"""Verbo de acao por item: estrategico -> 'falar sobre'; senao, o default da secao."""
if item.get("estrategico"):
return "falar sobre"
acao, _ = SEC_META.get(section, (None, None))
return acao
def _render_item(item: dict[str, Any], section: str) -> str:
"""<nome solto> | campo=valor | ... (com tratamento especial p/ Outros Valores)."""
desc = str(item.get("desc", "")).strip()
value = item.get("value")
if section == "Outros Valores":
match = _RX_OUTROS.match(desc)
if match:
parts = [match.group(1).strip().lower()]
if value is not None and value != "Incluído":
parts.append(f"valor={_fmt_money(value)}")
parts.append(f'ref="{match.group(2).strip()}"')
return " | ".join(parts)
parts = [desc]
if value is not None and value != "Incluído":
parts.append(f"valor={_fmt_money(value)}")
period = item.get("period")
if period and not is_period_range(period):
parts.append(f"data={period}")
if item.get("franchise"):
parts.append(f"franquia={item['franchise']}")
if item.get("consumption"):
parts.append(f"consumo={item['consumption']}")
if item.get("installment"):
parts.append(f"parcela={item['installment']}")
return " | ".join(parts)
# Seções omitidas no modo enxuto (intent classifier): o classificador só precisa
# dos NOMES dos itens por linha/seção, não de totais, planos nem juros/multas.
_LEAN_SKIP_SECTIONS = frozenset({"Fatura Resumo", "Planos", "Outros Valores"})
def to_text(data: dict[str, Any], *, lean: bool = False) -> str:
"""Converte o JSON normalizado de uma fatura no formato textual em blocos.
``lean=True`` (formato do intent classifier): mantém a estrutura LINHA/seção,
o NOME dos itens e o ``valor``/``data`` por item — descarta "Fatura Resumo",
"Planos", "Outros Valores" e os demais campos por-item (ação, type, franquia,
consumo). O ``valor``/``data`` distinguem cobranças duplicadas do mesmo nome na
mesma linha (desambiguação de cobrança). O orquestrador usa ``lean=False``
(formato completo, com ações)."""
lines: list[str] = []
msisdn_count = 0
# FATURA (achatada) — omitida no modo enxuto.
resumo = data.get("Fatura Resumo")
if not lean and isinstance(resumo, list):
lines.append("Fatura Resumo")
for item in resumo:
desc = item.get("desc", "?")
if "period" in item:
lines.append(f" {_snake(desc)}={item['period']}")
elif "emissao" in item:
lines.append(f" {_snake(desc)}={item['emissao']}")
elif "value" in item:
lines.append(f" {_snake(desc)}={_fmt_money(item['value'])}")
lines.append("")
# LINHAS (MSISDN)
for key, block in data.items():
if key in ("Fatura Resumo", "vocalized_msisdn"):
continue
if not isinstance(block, dict):
continue
msisdn_count += 1
lines.append(f"LINHA {key}")
# Planos — omitido no modo enxuto.
planos = block.get("Planos")
if not lean and isinstance(planos, dict) and planos:
lines.append("Planos")
for nome, plano in planos.items():
bits = [f"nome={nome}"]
if plano.get("period"):
bits.append(f"período={plano['period']}")
if plano.get("days") is not None:
bits.append(f"dias={plano['days']}")
bits.append(f"valor_final={_fmt_money(plano.get('valor_final'))}")
if plano.get("valor_bruto") not in (None, plano.get("valor_final")):
bits.append(f"valor_bruto={_fmt_money(plano.get('valor_bruto'))}")
if plano.get("total_descontos"):
bits.append(f"total_desc={_fmt_money(plano.get('total_descontos'))}")
if plano.get("is_controle"):
bits.append("controle=sim")
lines.append(" " + " | ".join(bits))
descontos = plano.get("descontos") or []
if descontos:
lines.append(" descontos:")
for desconto in descontos:
dbits = [
f"nome={desconto.get('desc')}",
f"valor={_fmt_money(desconto.get('value'))}",
]
if desconto.get("installment"):
dbits.append(f"parcela={desconto['installment']}")
lines.append(" " + " | ".join(dbits))
# Seções agrupadas pelo RÓTULO do cabeçalho (``SECTION_LABELS``): as que
# compartilham rótulo saem sob um único cabeçalho, na posição da primeira
# delas. Cada item guarda a seção de ORIGEM, que é quem decide a ação/classe
# por item — o rótulo é só apresentação.
groups: dict[str, tuple[str, list[tuple[str, dict[str, Any]]]]] = {}
for section, items in block.items():
if section == "Planos" or not isinstance(items, list):
continue
if lean and section in _LEAN_SKIP_SECTIONS:
continue
label = SECTION_LABELS.get(section, section)
_, entries = groups.setdefault(label, (section, []))
entries.extend((section, item) for item in items)
for label, (first_section, entries) in groups.items():
acao, classe = SEC_META.get(first_section, (None, None))
header = label
# No modo enxuto o cabeçalho é só o nome da seção (sem ação/classe).
if not lean and first_section in COBRADOS_A_PARTE_SECTIONS:
header += " | cobrados a parte"
elif acao and first_section not in PER_ITEM_ACTION_SECTIONS and not lean:
header += f" | ação={acao} | {CLASSE_LABELS.get(classe, classe)}"
lines.append(header)
for section, item in entries:
if lean:
# Nome do item + valor + data da cobrança (sem ação/type/
# franquia/consumo). O valor/data por item permitem o classifier
# DISTINGUIR N cobranças do mesmo nome na mesma linha (mesmo
# desc/msisdn, períodos diferentes) na desambiguação de cobrança
# duplicada — o msisdn vem do cabeçalho ``LINHA``. Itens
# ``Incluído`` (bundle) e períodos em faixa (ciclo da fatura, não
# data de cobrança) seguem só com o nome, como antes.
desc = str(item.get("desc", "")).strip()
if not desc:
continue
parts = [desc]
value = item.get("value")
if value is not None and value != "Incluído":
parts.append(f"valor={_fmt_money(value)}")
period = item.get("period")
if period and not is_period_range(period):
parts.append(f"data={period}")
lines.append(" " + " | ".join(parts))
continue
line = " " + _render_item(item, section)
if section in PER_ITEM_ACTION_SECTIONS:
item_acao = _item_acao(item, section)
if item_acao:
line += f" | ação={item_acao}"
if item.get("estrategico"):
line += " | type=estrategico"
lines.append(line)
lines.append("")
text = "\n".join(lines).rstrip()
if msisdn_count > 1:
text += "\n\nmultiplas_linhas = true"
else:
text += "\n\nmultiplas_linhas = false"
return text + "\n"
# ordem pedida pelo produto: avulso -> estrategico -> bundle
# (difere da ordem informacional bundle/estrategico/avulso usada em backend.py)
_VAS_PRODUCT_ORDER = ("avulso", "estrategico", "bundle")
def get_vas_product_names(data: dict[str, Any]) -> str:
"""Nomes dos VAS (avulso, estrategico, bundle — nessa ordem) da fatura
normalizada, deduplicados e separados por vírgula. Ex.: "Focus Mensal,
Tamboro Mensal". Ignora plano e demais seções não-VAS. Retorna "" se não houver."""
buckets: dict[str, list[str]] = {c: [] for c in _VAS_PRODUCT_ORDER}
seen: set[str] = set()
for key, block in data.items():
if key in ("Fatura Resumo", "vocalized_msisdn") or not isinstance(block, dict):
continue
for section, items in block.items():
if section == "Planos" or not isinstance(items, list):
continue
for item in items:
classe = item.get("classe")
if not classe and item.get("estrategico"):
classe = "estrategico"
if classe not in buckets:
continue
name = str(item.get("desc", "")).strip()
if not name or name in seen:
continue
seen.add(name)
buckets[classe].append(name)
ordered = [n for c in _VAS_PRODUCT_ORDER for n in buckets[c]]
return ", ".join(ordered)
def render_for_prompt(invoice_detail: Any, *, lean: bool = False) -> str | None:
"""Renderiza ``invoice_detail`` (dict ou str JSON) no formato textual ``to_text``
para uso no prompt. Fonte única compartilhada pelo orquestrador (system prompt)
e pelo intent classifier — garante que ambos leiam a MESMA fatura, sem drift.
``lean=True`` produz o formato enxuto do intent classifier (nomes + valor/data
por item, por linha/seção; ver :func:`to_text`); o orquestrador usa ``lean=False``.
Retorna ``None`` quando o formato textual está desligado (``USE_TEXT_FORMAT``
false) ou em qualquer falha de parse/render — cabe ao chamador decidir o
fallback (JSON cru no orquestrador; renderizador compacto no classifier).
Nunca levanta exceção: o prompt não pode quebrar por causa da fatura."""
if not (USE_TEXT_FORMAT and invoice_detail):
return None
try:
parsed = (
json.loads(invoice_detail)
if isinstance(invoice_detail, str)
else invoice_detail
)
if isinstance(parsed, dict) and parsed:
return to_text(parsed, lean=lean)
except Exception: # noqa: BLE001 — nunca quebrar o prompt
logger.warning("invoice_to_text.render_for_prompt falhou", exc_info=True)
return None