normalize unmatched preview values

app/processor.py

@@ -341,6 +341,7 @@ def _postprocess_workbook(
 ) -> None:
     workbook = load_workbook(path)
     try:
+        _normalize_unmatched_columns(workbook)
         summary_records = _collect_summary_records(workbook)
 
         if not include_unmatched_items:
@@ -362,6 +363,46 @@ def _postprocess_workbook(
         workbook.close()
 
 
+def _normalize_unmatched_columns(workbook) -> None:
+    for sheet in workbook.worksheets:
+        if sheet.title == "未检测到内容汇总" or sheet.max_row < 2:
+            continue
+
+        header = [_cell_text(sheet.cell(1, col).value) for col in range(1, sheet.max_column + 1)]
+        unmatched_index = _find_header_index(header, "未匹配检测内容")
+        if unmatched_index is None:
+            continue
+
+        marker_col = unmatched_index + 1
+        parsed_rows: list[dict[str, str]] = []
+        item_names: list[str] = []
+        for row_index in range(2, sheet.max_row + 1):
+            raw_values = [
+                _cell_text(sheet.cell(row_index, col).value)
+                for col in range(marker_col, sheet.max_column + 1)
+            ]
+            parsed = _parse_unmatched_items([value for value in raw_values if value])
+            parsed_rows.append(parsed)
+            for item_name in parsed:
+                if item_name not in item_names:
+                    item_names.append(item_name)
+
+        if sheet.max_column >= marker_col:
+            sheet.delete_cols(marker_col, sheet.max_column - marker_col + 1)
+
+        sheet.cell(1, marker_col).value = "未匹配检测内容"
+        sheet.cell(1, marker_col).font = Font(bold=True)
+        for offset, item_name in enumerate(item_names, start=1):
+            cell = sheet.cell(1, marker_col + offset)
+            cell.value = item_name
+            cell.font = Font(bold=True)
+
+        for row_index, parsed in enumerate(parsed_rows, start=2):
+            sheet.cell(row_index, marker_col).value = ""
+            for offset, item_name in enumerate(item_names, start=1):
+                sheet.cell(row_index, marker_col + offset).value = parsed.get(item_name, "")
+
+
 def _collect_summary_records(workbook) -> list[dict[str, object]]:
     records: list[dict[str, object]] = []
     for sheet in workbook.worksheets:
@@ -380,12 +421,13 @@ def _collect_summary_records(workbook) -> list[dict[str, object]]:
                 _cell_text(sheet.cell(row_index, col).value)
                 for col in range(5, unmatched_col + 1)
             ]
-            unmatched_values = [
-                _cell_text(sheet.cell(row_index, col).value)
-                for col in range(unmatched_col + 1, sheet.max_column + 1)
-            ]
-            unmatched_values = [value for value in unmatched_values if value]
-            if not unmatched_values:
+            item_values = {
+                _cell_text(sheet.cell(1, col).value): _cell_text(sheet.cell(row_index, col).value)
+                for col in range(unmatched_col + 2, sheet.max_column + 1)
+                if _cell_text(sheet.cell(1, col).value)
+            }
+            item_values = {name: value for name, value in item_values.items() if value}
+            if not item_values:
                 continue
             if not _all_standard_values_missing(standard_values):
                 continue
@@ -396,7 +438,7 @@ def _collect_summary_records(workbook) -> list[dict[str, object]]:
                     "sample_time": base_values[2],
                     "reason": base_values[3],
                     "sheet": sheet.title,
-                    "items": _parse_unmatched_items(unmatched_values),
+                    "items": item_values,
                 }
             )
     return records