重构项目为LLM 驱动

src/doc/extractor.py

@@ -0,0 +1,65 @@
+"""发票提取编排
+
+串联 PDF 读取 → LLM 提取 → 支付截图匹配 → 分类，生成支付记录列表。
+
+对外接口:
+    extract_invoices(directory) -> tuple[list[dict], dict]
+"""
+
+from .. import get_logger
+from .invoice import classify_invoice_batch
+from .llm_extractor import extract_invoice_from_text
+from .matcher import match_invoices_to_cards
+from .pdf import extract_text_from_pdf, find_pdf_files
+
+log = get_logger("extractor")
+
+
+def extract_invoices(
+    directory: str = ".",
+) -> tuple[list[dict[str, str]], dict[str, list[dict[str, str]]]]:
+    """扫描目录下所有 PDF,提取发票信息并匹配支付记录
+
+    Returns:
+        (payment_records, groups): 支付记录列表和按发票类型分组的字典
+            groups = {'travel': [差旅发票], 'general': [普通发票]}
+    """
+    pdf_files = find_pdf_files(directory)
+    if not pdf_files:
+        log.warning("未找到 PDF 文件")
+        return [], {"travel": [], "general": []}
+
+    log.info(f"发现 {len(pdf_files)} 个 PDF 文件")
+
+    all_invoices = []
+    for pdf_path in pdf_files:
+        text = extract_text_from_pdf(pdf_path)
+        if not text:
+            log.warning(f"未能提取文本: {pdf_path.name}")
+            continue
+
+        invoice = extract_invoice_from_text(text, pdf_path.name)
+
+        if invoice and invoice.get("发票号码"):
+            all_invoices.append(invoice)
+            log.info(f"[{invoice['发票类型']}] 已解析: {pdf_path.name}")
+        else:
+            log.warning(f"未能解析: {pdf_path.name}")
+
+    if all_invoices:
+        log.info(f"共处理 {len(all_invoices)} 张发票")
+    else:
+        log.warning("未成功解析任何发票")
+
+    # 将支付截图与发票进行金额匹配，返回以支付记录为主键的列表
+    payment_records = match_invoices_to_cards(all_invoices, directory)
+
+    # 从支付记录中还原所有发票用于分类
+    all_invoices_restored: list[dict[str, str]] = []
+    for record in payment_records:
+        all_invoices_restored.extend(record.get("_matched_invoices", []))
+
+    groups = classify_invoice_batch(all_invoices_restored)
+    log.info(f"差旅发票: {len(groups['travel'])} 张, 普通发票: {len(groups['general'])} 张")
+
+    return payment_records, groups