add result preview and exports

app/processor.py

@@ -3,8 +3,11 @@ import shutil
 import subprocess
 import sys
 import zipfile
+from dataclasses import dataclass
 from pathlib import Path
 
+from openpyxl import load_workbook
+
 
 PROCESSOR_DIR = Path(__file__).resolve().parent / "processors"
 
@@ -13,6 +16,30 @@ class ProcessingError(Exception):
     pass
 
 
+@dataclass
+class SheetSummary:
+    name: str
+    rows: int
+    columns: int
+    preview: list[list[str]]
+
+
+@dataclass
+class ExcelSummary:
+    filename: str
+    relpath: str
+    sheets: list[SheetSummary]
+
+
+@dataclass
+class ProcessingResult:
+    job_id: str
+    mode: str
+    output_dir: Path
+    zip_path: Path
+    files: list[ExcelSummary]
+
+
 def run_processing(
     zip_path: Path,
     job_dir: Path,
@@ -21,7 +48,7 @@ def run_processing(
     result_name: str,
     show_not_match: bool,
     show_all_infos: bool,
-) -> Path:
+) -> ProcessingResult:
     if mode not in {"auto", "v1", "v2"}:
         raise ProcessingError("处理模式不正确。")
     if data_type not in {"pat_no", "zhuyuanhao"}:
@@ -82,8 +109,7 @@ def run_processing(
         timeout=60 * 30,
     )
 
-    log_path = output_dir / "process.log"
-    log_path.write_text(
+    (job_dir / "process.log").write_text(
         "mode=" + selected_mode + "\n\n" + completed.stdout,
         encoding="utf-8",
     )
@@ -92,20 +118,41 @@ def run_processing(
 
     if selected_mode == "v2":
         _collect_v2_outputs(data_dir, output_dir)
-    _collect_logs(data_dir, output_dir)
 
-    xlsx_files = list(output_dir.rglob("*.xlsx"))
+    xlsx_files = sorted(output_dir.rglob("*.xlsx"))
     if not xlsx_files:
-        raise ProcessingError("处理完成但没有生成 Excel 文件，请检查数据结构和 process.log。")
+        raise ProcessingError("处理完成但没有生成 Excel 文件，请检查数据结构。")
 
     result_zip = job_dir / "result.zip"
-    with zipfile.ZipFile(result_zip, "w", compression=zipfile.ZIP_DEFLATED) as zf:
-        for path in output_dir.rglob("*"):
-            if path.is_file():
-                zf.write(path, path.relative_to(output_dir))
+    _create_result_zip(output_dir, result_zip)
+    return ProcessingResult(
+        job_id=job_dir.name,
+        mode=selected_mode,
+        output_dir=output_dir,
+        zip_path=result_zip,
+        files=[_summarize_workbook(path, output_dir) for path in xlsx_files],
+    )
+
+
+def create_result_zip(job_dir: Path) -> Path:
+    output_dir = job_dir / "output"
+    result_zip = job_dir / "result.zip"
+    if not output_dir.exists():
+        raise ProcessingError("结果目录不存在。")
+    _create_result_zip(output_dir, result_zip)
     return result_zip
 
 
+def find_output_file(job_dir: Path, relpath: str) -> Path:
+    output_dir = (job_dir / "output").resolve()
+    target = (output_dir / relpath).resolve()
+    if not str(target).startswith(str(output_dir)) or not target.is_file():
+        raise ProcessingError("结果文件不存在。")
+    if target.suffix.lower() != ".xlsx":
+        raise ProcessingError("只能导出 Excel 结果文件。")
+    return target
+
+
 def _safe_extract(zip_path: Path, target_dir: Path) -> None:
     try:
         with zipfile.ZipFile(zip_path) as zf:
@@ -169,13 +216,41 @@ def _collect_v2_outputs(data_dir: Path, output_dir: Path) -> None:
             shutil.copy2(path, target)
 
 
-def _collect_logs(data_dir: Path, output_dir: Path) -> None:
-    logs_dir = output_dir / "logs"
-    for pattern in ("*.txt", "error.txt", "Error.txt"):
-        for path in data_dir.rglob(pattern):
+def _create_result_zip(output_dir: Path, result_zip: Path) -> None:
+    with zipfile.ZipFile(result_zip, "w", compression=zipfile.ZIP_DEFLATED) as zf:
+        for path in sorted(output_dir.rglob("*.xlsx")):
             if path.is_file():
-                logs_dir.mkdir(exist_ok=True)
-                relative = path.relative_to(data_dir)
-                target = logs_dir / relative
-                target.parent.mkdir(parents=True, exist_ok=True)
-                shutil.copy2(path, target)
+                zf.write(path, path.relative_to(output_dir))
+
+
+def _summarize_workbook(path: Path, output_dir: Path) -> ExcelSummary:
+    sheets: list[SheetSummary] = []
+    workbook = load_workbook(path, read_only=True, data_only=True)
+    try:
+        for sheet in workbook.worksheets:
+            preview: list[list[str]] = []
+            for row in sheet.iter_rows(max_row=6, values_only=True):
+                preview.append([_cell_to_text(value) for value in row])
+            sheets.append(
+                SheetSummary(
+                    name=sheet.title,
+                    rows=sheet.max_row or 0,
+                    columns=sheet.max_column or 0,
+                    preview=preview,
+                )
+            )
+    finally:
+        workbook.close()
+
+    return ExcelSummary(
+        filename=path.name,
+        relpath=path.relative_to(output_dir).as_posix(),
+        sheets=sheets,
+    )
+
+
+def _cell_to_text(value: object) -> str:
+    if value is None:
+        return ""
+    text = str(value)
+    return text if len(text) <= 80 else text[:77] + "..."