move empty not-find rows to summary

README.md

@@ -33,7 +33,7 @@ V2：zip 解压后包含 `Patients_info.csv`，并按患者目录分别保存检
 
 患者编号类型可选择自动识别。自动识别会读取 `Patients_info.csv` 中的 `pat_no`，并与 `Tests_List` 文件名或患者目录名比对：若更匹配 10 位补零编号，则使用 `pat_no`；若更匹配原始编号，则使用 `zhuyuanhao`。
 
-系统默认输出完整结果；处理完成后可在结果页通过“内容选择”立即切换预览内容，并同步影响右侧“导出此 Excel”的文件内容。可选择是否保留：
+系统默认输出完整结果；处理完成后可在结果页通过“内容选择”立即切换预览内容，并同步影响右侧“导出此 Excel”的文件内容。结果页还可以按姓名、采样时间或检测原因选择升序/降序排序；“未检测到内容汇总”会在每个分组标题下单独排序，不会把不同检测原因的分组混在一起。可选择是否保留：
 
 - 基本工作表
 - 未匹配检测内容项

app/main.py

@@ -23,6 +23,15 @@ WORK_ROOT.mkdir(parents=True, exist_ok=True)
 
 APP_TITLE = "\u68c0\u6d4b\u6570\u636e\u5904\u7406"
 UNMATCHED = "\u672a\u5339\u914d\u68c0\u6d4b\u5185\u5bb9"
+SORT_OPTIONS = {
+    "name": "\u59d3\u540d",
+    "sample_time": "\u91c7\u6837\u65f6\u95f4",
+    "reason": "\u68c0\u6d4b\u539f\u56e0",
+}
+SORT_ORDERS = {
+    "asc": "\u5347\u5e8f",
+    "desc": "\u964d\u5e8f",
+}
 
 app = FastAPI(title=APP_TITLE)
 
@@ -117,16 +126,22 @@ def result_page(
     include_basic_sheets: bool = Query(True),
     include_unmatched_items: bool = Query(True),
     include_summary_sheet: bool = Query(True),
+    sort_by: str = Query("sample_time"),
+    sort_order: str = Query("asc"),
 ) -> str:
     job_dir = _get_job_dir(job_id)
     try:
         rows = _clean_preview_rows(preview_rows)
+        clean_sort_by = _clean_sort_by(sort_by)
+        clean_sort_order = _clean_sort_order(sort_order)
         result = summarize_job(
             job_dir,
             rows,
             include_basic_sheets=include_basic_sheets,
             include_unmatched_items=include_unmatched_items,
             include_summary_sheet=include_summary_sheet,
+            sort_by=clean_sort_by,
+            sort_order=clean_sort_order,
         )
     except ProcessingError as exc:
         raise HTTPException(status_code=404, detail=str(exc)) from exc
@@ -136,6 +151,8 @@ def result_page(
         include_basic_sheets=include_basic_sheets,
         include_unmatched_items=include_unmatched_items,
         include_summary_sheet=include_summary_sheet,
+        sort_by=clean_sort_by,
+        sort_order=clean_sort_order,
     )
 
 
@@ -145,6 +162,8 @@ def download_all(
     include_basic_sheets: bool = Query(True),
     include_unmatched_items: bool = Query(True),
     include_summary_sheet: bool = Query(True),
+    sort_by: str = Query("sample_time"),
+    sort_order: str = Query("asc"),
 ) -> FileResponse:
     job_dir = _get_job_dir(job_id)
     try:
@@ -153,6 +172,8 @@ def download_all(
             include_basic_sheets=include_basic_sheets,
             include_unmatched_items=include_unmatched_items,
             include_summary_sheet=include_summary_sheet,
+            sort_by=_clean_sort_by(sort_by),
+            sort_order=_clean_sort_order(sort_order),
         )
     except ProcessingError as exc:
         raise HTTPException(status_code=404, detail=str(exc)) from exc
@@ -166,6 +187,8 @@ def download_file(
     include_basic_sheets: bool = Query(True),
     include_unmatched_items: bool = Query(True),
     include_summary_sheet: bool = Query(True),
+    sort_by: str = Query("sample_time"),
+    sort_order: str = Query("asc"),
 ) -> FileResponse:
     job_dir = _get_job_dir(job_id)
     try:
@@ -175,6 +198,8 @@ def download_file(
             include_basic_sheets=include_basic_sheets,
             include_unmatched_items=include_unmatched_items,
             include_summary_sheet=include_summary_sheet,
+            sort_by=_clean_sort_by(sort_by),
+            sort_order=_clean_sort_order(sort_order),
         )
     except ProcessingError as exc:
         raise HTTPException(status_code=404, detail=str(exc)) from exc
@@ -207,12 +232,26 @@ def _checked(value: bool) -> str:
     return "checked" if value else ""
 
 
+def _selected(value: str, current: str) -> str:
+    return "selected" if value == current else ""
+
+
+def _clean_sort_by(sort_by: str) -> str:
+    return sort_by if sort_by in SORT_OPTIONS else "sample_time"
+
+
+def _clean_sort_order(sort_order: str) -> str:
+    return sort_order if sort_order in SORT_ORDERS else "asc"
+
+
 def _render_result(
     result: ProcessingResult,
     preview_rows: int = 20,
     include_basic_sheets: bool = True,
     include_unmatched_items: bool = True,
     include_summary_sheet: bool = True,
+    sort_by: str = "sample_time",
+    sort_order: str = "asc",
 ) -> str:
     total_sheets = sum(len(file.sheets) for file in result.files)
     total_rows = sum(max(sheet.rows - 1, 0) for file in result.files for sheet in file.sheets)
@@ -230,6 +269,16 @@ def _render_result(
         <label><input class="export-option" type="checkbox" data-param="include_basic_sheets" {_checked(include_basic_sheets)}> \u57fa\u672c\u5de5\u4f5c\u8868</label>
         <label><input class="export-option" type="checkbox" data-param="include_unmatched_items" {_checked(include_unmatched_items)}> \u672a\u5339\u914d\u68c0\u6d4b\u5185\u5bb9\u9879</label>
         <label><input class="export-option" type="checkbox" data-param="include_summary_sheet" {_checked(include_summary_sheet)}> \u672a\u68c0\u6d4b\u5230\u5185\u5bb9\u6c47\u603b\u8868</label>
+        <label for="sort_by">\u6392\u5e8f</label>
+        <select id="sort_by" class="result-option" data-param="sort_by">
+          <option value="name" {_selected("name", sort_by)}>\u6309\u59d3\u540d</option>
+          <option value="sample_time" {_selected("sample_time", sort_by)}>\u6309\u91c7\u6837\u65f6\u95f4</option>
+          <option value="reason" {_selected("reason", sort_by)}>\u6309\u68c0\u6d4b\u539f\u56e0</option>
+        </select>
+        <select id="sort_order" class="result-option" data-param="sort_order">
+          <option value="asc" {_selected("asc", sort_order)}>\u5347\u5e8f</option>
+          <option value="desc" {_selected("desc", sort_order)}>\u964d\u5e8f</option>
+        </select>
       </section>
       <form class="row-control" method="get" action="/result/{html.escape(result.job_id)}">
         <label for="preview_rows">\u6bcf\u4e2a\u5de5\u4f5c\u8868\u9884\u89c8\u884c\u6570</label>
@@ -411,6 +460,11 @@ def _page_shell(
       margin: 0;
       font-weight: 500;
     }}
+    .export-options select {{
+      width: auto;
+      min-width: 128px;
+      padding: 8px 10px;
+    }}
     .checks label {{
       display: inline-flex;
       align-items: center;
@@ -591,6 +645,9 @@ def _page_shell(
       const options = Array.from(document.querySelectorAll('.export-option'));
       const params = new URLSearchParams();
       options.forEach((option) => params.set(option.dataset.param, option.checked ? 'true' : 'false'));
+      document.querySelectorAll('.result-option').forEach((option) => {{
+        params.set(option.dataset.param, option.value);
+      }});
       document.querySelectorAll('.export-link').forEach((link) => {{
         const base = link.dataset.base;
         const sep = base.includes('?') ? '&' : '?';
@@ -606,6 +663,9 @@ def _page_shell(
       document.querySelectorAll('.export-option').forEach((option) => {{
         url.searchParams.set(option.dataset.param, option.checked ? 'true' : 'false');
       }});
+      document.querySelectorAll('.result-option').forEach((option) => {{
+        url.searchParams.set(option.dataset.param, option.value);
+      }});
       window.location.href = url.toString();
     }}
     const resultForm = document.querySelector('.row-control');
@@ -619,6 +679,10 @@ def _page_shell(
       updateExportLinks();
       refreshResultWithOptions();
     }}));
+    document.querySelectorAll('.result-option').forEach((option) => option.addEventListener('change', () => {{
+      updateExportLinks();
+      refreshResultWithOptions();
+    }}));
     updateExportLinks();
   </script>
 </body>

app/processor.py

@@ -6,6 +6,7 @@ import sys
 import uuid
 import zipfile
 from dataclasses import dataclass
+from datetime import datetime
 from pathlib import Path
 
 from openpyxl import load_workbook
@@ -17,6 +18,8 @@ PROCESSOR_DIR = Path(__file__).resolve().parent / "processors"
 SUMMARY_SHEET_NAME = "\u672a\u68c0\u6d4b\u5230\u5185\u5bb9\u6c47\u603b"
 UNMATCHED_HEADER = "\u672a\u5339\u914d\u68c0\u6d4b\u5185\u5bb9"
 UNMATCHED_FILL = PatternFill(fill_type="solid", fgColor="FCE4D6")
+SORT_FIELDS = {"none", "name", "sample_time", "reason"}
+SORT_ORDERS = {"asc", "desc"}
 
 
 class ProcessingError(Exception):
@@ -59,6 +62,8 @@ def run_processing(
     include_basic_sheets: bool = True,
     include_unmatched_items: bool = True,
     include_summary_sheet: bool = True,
+    sort_by: str = "sample_time",
+    sort_order: str = "asc",
 ) -> ProcessingResult:
     if mode not in {"auto", "v1", "v2"}:
         raise ProcessingError("处理模式不正确。")
@@ -142,6 +147,8 @@ def run_processing(
             include_basic_sheets=include_basic_sheets,
             include_unmatched_items=include_unmatched_items,
             include_summary_sheet=include_summary_sheet,
+            sort_by=sort_by,
+            sort_order=sort_order,
         )
 
     result_zip = job_dir / "result.zip"
@@ -160,6 +167,8 @@ def create_result_zip(
     include_basic_sheets: bool = True,
     include_unmatched_items: bool = True,
     include_summary_sheet: bool = True,
+    sort_by: str = "sample_time",
+    sort_order: str = "asc",
 ) -> Path:
     output_dir = job_dir / "output"
     result_zip = job_dir / "result.zip"
@@ -176,6 +185,8 @@ def create_result_zip(
                 include_basic_sheets=include_basic_sheets,
                 include_unmatched_items=include_unmatched_items,
                 include_summary_sheet=include_summary_sheet,
+                sort_by=sort_by,
+                sort_order=sort_order,
             )
 
     result_zip = export_dir / "result.zip"
@@ -189,6 +200,8 @@ def summarize_job(
     include_basic_sheets: bool = True,
     include_unmatched_items: bool = True,
     include_summary_sheet: bool = True,
+    sort_by: str = "sample_time",
+    sort_order: str = "asc",
 ) -> ProcessingResult:
     output_dir = job_dir / "output"
     if not output_dir.exists():
@@ -204,6 +217,8 @@ def summarize_job(
                 include_basic_sheets=include_basic_sheets,
                 include_unmatched_items=include_unmatched_items,
                 include_summary_sheet=include_summary_sheet,
+                sort_by=sort_by,
+                sort_order=sort_order,
             )
 
     xlsx_files = sorted(preview_dir.rglob("*.xlsx"))
@@ -226,6 +241,8 @@ def find_output_file(
     include_basic_sheets: bool = True,
     include_unmatched_items: bool = True,
     include_summary_sheet: bool = True,
+    sort_by: str = "sample_time",
+    sort_order: str = "asc",
 ) -> Path:
     output_dir = (job_dir / "output").resolve()
     target = (output_dir / relpath).resolve()
@@ -241,6 +258,8 @@ def find_output_file(
         include_basic_sheets=include_basic_sheets,
         include_unmatched_items=include_unmatched_items,
         include_summary_sheet=include_summary_sheet,
+        sort_by=sort_by,
+        sort_order=sort_order,
     )
     return export_target
 
@@ -258,6 +277,8 @@ def _apply_export_options(
     include_basic_sheets: bool,
     include_unmatched_items: bool,
     include_summary_sheet: bool,
+    sort_by: str,
+    sort_order: str,
 ) -> None:
     if not include_basic_sheets and not include_summary_sheet:
         raise ProcessingError("\u81f3\u5c11\u9700\u8981\u5bfc\u51fa\u57fa\u672c\u5de5\u4f5c\u8868\u6216\u672a\u68c0\u6d4b\u5230\u5185\u5bb9\u6c47\u603b\u8868\u3002")
@@ -278,6 +299,7 @@ def _apply_export_options(
         if not workbook.worksheets:
             workbook.create_sheet(SUMMARY_SHEET_NAME)
 
+        _sort_workbook(workbook, sort_by, sort_order)
         workbook.save(path)
     finally:
         workbook.close()
@@ -434,12 +456,15 @@ def _postprocess_workbook(
     include_basic_sheets: bool,
     include_unmatched_items: bool,
     include_summary_sheet: bool,
+    sort_by: str,
+    sort_order: str,
 ) -> None:
     workbook = load_workbook(path)
     try:
         _normalize_unmatched_columns(workbook)
-        _remove_empty_not_find_rows(workbook)
         summary_records = _collect_summary_records(workbook)
+        _remove_not_found_rows(workbook)
+        _remove_empty_unmatched_columns(workbook)
 
         if not include_unmatched_items:
             _remove_unmatched_columns(workbook)
@@ -455,6 +480,7 @@ def _postprocess_workbook(
         if not workbook.worksheets:
             workbook.create_sheet(SUMMARY_SHEET_NAME)
 
+        _sort_workbook(workbook, sort_by, sort_order)
         workbook.save(path)
     finally:
         workbook.close()
@@ -484,13 +510,14 @@ def _normalize_unmatched_columns(workbook) -> None:
                 if item_name not in item_names:
                     item_names.append(item_name)
 
+        if not item_names:
             if sheet.max_column >= marker_col:
                 sheet.delete_cols(marker_col, sheet.max_column - marker_col + 1)
-
-        if not item_names:
-            sheet.delete_cols(marker_col, 1)
             continue
 
+        if sheet.max_column >= marker_col:
+            sheet.delete_cols(marker_col, sheet.max_column - marker_col + 1)
+
         sheet.cell(1, marker_col).value = UNMATCHED_HEADER
         sheet.cell(1, marker_col).font = Font(bold=True)
         sheet.cell(1, marker_col).fill = UNMATCHED_FILL
@@ -509,7 +536,7 @@ def _normalize_unmatched_columns(workbook) -> None:
                 cell.fill = UNMATCHED_FILL
 
 
-def _remove_empty_not_find_rows(workbook) -> None:
+def _remove_not_found_rows(workbook) -> None:
     for sheet in workbook.worksheets:
         if sheet.title == SUMMARY_SHEET_NAME or sheet.max_row < 2:
             continue
@@ -522,13 +549,7 @@ def _remove_empty_not_find_rows(workbook) -> None:
                 _cell_text(sheet.cell(row_index, col).value)
                 for col in range(5, standard_end + 1)
             ]
-            unmatched_values = []
+            if _all_standard_values_missing(standard_values):
-            if unmatched_index is not None:
-                unmatched_values = [
-                    _cell_text(sheet.cell(row_index, col).value)
-                    for col in range(unmatched_index + 2, sheet.max_column + 1)
-                ]
-            if _all_standard_values_missing(standard_values) and not any(unmatched_values):
                 sheet.delete_rows(row_index, 1)
 
 
@@ -539,8 +560,7 @@ def _collect_summary_records(workbook) -> list[dict[str, object]]:
             continue
         header = [_cell_text(sheet.cell(1, col).value) for col in range(1, sheet.max_column + 1)]
         unmatched_col = _find_header_index(header, UNMATCHED_HEADER)
-        if unmatched_col is None:
+        standard_end = unmatched_col if unmatched_col is not None else sheet.max_column
-            continue
 
         for row_index in range(2, sheet.max_row + 1):
             base_values = [_cell_text(sheet.cell(row_index, col).value) for col in range(1, 5)]
@@ -548,18 +568,13 @@ def _collect_summary_records(workbook) -> list[dict[str, object]]:
                 continue
             standard_values = [
                 _cell_text(sheet.cell(row_index, col).value)
-                for col in range(5, unmatched_col + 1)
+                for col in range(5, standard_end + 1)
             ]
-            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
+            item_values = _summary_item_values(sheet, row_index, header, unmatched_col, standard_end)
+            if not item_values:
+                continue
             records.append(
                 {
                     "name": base_values[0],
@@ -573,6 +588,31 @@ def _collect_summary_records(workbook) -> list[dict[str, object]]:
     return records
 
 
+def _summary_item_values(
+    sheet,
+    row_index: int,
+    header: list[str],
+    unmatched_col: int | None,
+    standard_end: int,
+) -> dict[str, str]:
+    item_values: dict[str, str] = {}
+    if unmatched_col is not None:
+        for col in range(unmatched_col + 2, sheet.max_column + 1):
+            item_name = _cell_text(sheet.cell(1, col).value)
+            item_value = _cell_text(sheet.cell(row_index, col).value)
+            if item_name and item_value:
+                item_values[item_name] = item_value
+    if item_values:
+        return item_values
+
+    for col in range(5, standard_end + 1):
+        item_name = header[col - 1] if col - 1 < len(header) else ""
+        item_value = _cell_text(sheet.cell(row_index, col).value)
+        if item_name and item_value:
+            item_values[item_name] = item_value
+    return item_values
+
+
 def _replace_summary_sheet(workbook, records: list[dict[str, object]]) -> None:
     if SUMMARY_SHEET_NAME in workbook.sheetnames:
         workbook.remove(workbook[SUMMARY_SHEET_NAME])
@@ -631,6 +671,163 @@ def _remove_unmatched_columns(workbook) -> None:
             sheet.delete_cols(unmatched_col + 1, sheet.max_column - unmatched_col)
 
 
+def _remove_empty_unmatched_columns(workbook) -> None:
+    for sheet in workbook.worksheets:
+        if sheet.title == SUMMARY_SHEET_NAME or sheet.max_row < 1:
+            continue
+        header = [_cell_text(sheet.cell(1, col).value) for col in range(1, sheet.max_column + 1)]
+        unmatched_col = _find_header_index(header, UNMATCHED_HEADER)
+        if unmatched_col is None:
+            continue
+
+        first_col = unmatched_col + 1
+        item_cols = [
+            col
+            for col in range(first_col + 1, sheet.max_column + 1)
+            if _cell_text(sheet.cell(1, col).value)
+        ]
+        used_item_cols = [
+            col
+            for col in item_cols
+            if any(_cell_text(sheet.cell(row, col).value) for row in range(2, sheet.max_row + 1))
+        ]
+        if not used_item_cols:
+            sheet.delete_cols(first_col, sheet.max_column - unmatched_col)
+            continue
+
+        for col in reversed(item_cols):
+            if col not in used_item_cols:
+                sheet.delete_cols(col, 1)
+
+
+def _sort_workbook(workbook, sort_by: str, sort_order: str) -> None:
+    sort_by = sort_by if sort_by in SORT_FIELDS else "sample_time"
+    sort_order = sort_order if sort_order in SORT_ORDERS else "asc"
+    if sort_by == "none":
+        return
+
+    reverse = sort_order == "desc"
+    for sheet in workbook.worksheets:
+        if sheet.max_row < 3:
+            continue
+        if sheet.title == SUMMARY_SHEET_NAME:
+            _sort_summary_sheet(sheet, sort_by, reverse)
+        else:
+            _sort_regular_sheet(sheet, sort_by, reverse)
+
+
+def _sort_regular_sheet(sheet, sort_by: str, reverse: bool) -> None:
+    header = [_cell_text(sheet.cell(1, col).value) for col in range(1, sheet.max_column + 1)]
+    sort_col = _sort_column_from_header(header, sort_by)
+    if sort_col is None:
+        return
+
+    rows = _read_rows(sheet, 2, sheet.max_row)
+    _sort_rows(rows, sort_col, sort_by, reverse)
+    _write_rows(sheet, 2, rows)
+
+
+def _sort_summary_sheet(sheet, sort_by: str, reverse: bool) -> None:
+    row_index = 1
+    while row_index <= sheet.max_row:
+        row = [_cell_text(sheet.cell(row_index, col).value) for col in range(1, min(sheet.max_column, 4) + 1)]
+        if not _is_summary_header_values(row):
+            row_index += 1
+            continue
+
+        header = [_cell_text(sheet.cell(row_index, col).value) for col in range(1, sheet.max_column + 1)]
+        sort_col = _sort_column_from_header(header, sort_by)
+        if sort_col is None:
+            row_index += 1
+            continue
+
+        start = row_index + 1
+        end = start
+        while end <= sheet.max_row:
+            next_row = [
+                _cell_text(sheet.cell(end, col).value)
+                for col in range(1, min(sheet.max_column, 4) + 1)
+            ]
+            if _is_summary_header_values(next_row):
+                break
+            end += 1
+
+        if end > start:
+            rows = _read_rows(sheet, start, end - 1)
+            _sort_rows(rows, sort_col, sort_by, reverse)
+            _write_rows(sheet, start, rows)
+        row_index = end
+
+
+def _sort_column_from_header(header: list[str], sort_by: str) -> int | None:
+    if sort_by == "name":
+        names = ["姓名"]
+    elif sort_by == "sample_time":
+        names = ["采样时间"]
+    elif sort_by == "reason":
+        names = ["检测原因"]
+    else:
+        return None
+
+    for index, value in enumerate(header):
+        if any(value == name or value.startswith(name) for name in names):
+            return index
+    return None
+
+
+def _read_rows(sheet, start: int, end: int) -> list[list[object]]:
+    return [
+        [sheet.cell(row_index, col).value for col in range(1, sheet.max_column + 1)]
+        for row_index in range(start, end + 1)
+    ]
+
+
+def _write_rows(sheet, start: int, rows: list[list[object]]) -> None:
+    for offset, row in enumerate(rows):
+        row_index = start + offset
+        for col, value in enumerate(row, start=1):
+            sheet.cell(row_index, col).value = value
+
+
+def _sort_rows(rows: list[list[object]], sort_col: int, sort_by: str, reverse: bool) -> None:
+    rows.sort(key=lambda row: _sort_value(row[sort_col], sort_by))
+    if reverse:
+        filled = [row for row in rows if _cell_text(row[sort_col])]
+        empty = [row for row in rows if not _cell_text(row[sort_col])]
+        filled.reverse()
+        rows[:] = filled + empty
+
+
+def _sort_value(value: object, sort_by: str) -> tuple[int, object]:
+    text = _cell_text(value)
+    if not text:
+        return (1, "")
+    if sort_by == "sample_time":
+        parsed = _parse_datetime(text)
+        if parsed is not None:
+            return (0, parsed.isoformat())
+    return (0, text)
+
+
+def _parse_datetime(value: str) -> datetime | None:
+    for fmt in ("%Y-%m-%d %H:%M:%S", "%Y/%m/%d %H:%M:%S", "%Y-%m-%d", "%Y/%m/%d"):
+        try:
+            return datetime.strptime(value, fmt)
+        except ValueError:
+            continue
+    return None
+
+
+def _is_summary_header_values(row: list[str]) -> bool:
+    return (
+        len(row) >= 4
+        and row[0] == "姓名"
+        and row[1] == "住院号"
+        and row[2] == "采样时间"
+        and row[3].startswith("检测原因")
+    )
+
+
 def _find_header_index(header: list[str], name: str) -> int | None:
     for index, value in enumerate(header):
         if value == name: