Skip wide sparse columns without dropping later xlsx sheets

Why: review of EXT-5 found a column-cap cell (common styled XFD cells) wrongly reported the 200k-cell cap and aborted every remaining worksheet; malformed sheet XML was also dropped silently, contradicting the explicit-failure contract; the legacy-office parser id was missing from the registry.

Evidence: local GOWORK=off go test ./... 29 packages pass with new regressions (wide column keeps later sheets, bad sheet XML warns, registry maps doc/xls/ppt); go vet clean; recorded as SELF on the Dev task card.

Impact: xlsxSheetBlocks returns wide/badXML signals; wide cells skip with a per-sheet warning, cell-cap truncation unchanged; builtin:legacy-office added to ParsersDescription.

Refs: review of backend 727f370; documents proposal 2026-10-06-ext-5-host-parse-document sect.2.

internal/ingest/ingest.go

@@ -361,6 +361,7 @@ func ParsersDescription() []core.ParserDesc {
 		{ID: "builtin:pdf", Formats: []string{"pdf"}, Source: core.SourceBuiltin, Note: "文本层；扫描件为远期 MinerU 深度档"},
 		{ID: "builtin:xlsx", Formats: []string{"xlsx", "xlsm"}, Source: core.SourceBuiltin},
 		{ID: "builtin:pptx", Formats: []string{"pptx", "pptm", "ppsx"}, Source: core.SourceBuiltin},
+		{ID: "builtin:legacy-office", Formats: []string{"doc", "xls", "ppt"}, Source: core.SourceBuiltin, Note: "不解析；提示转存现代格式后重传"},
 		{ID: "mineru", Formats: []string{"pdf", "png", "jpg"}, Source: core.SourcePlugin, Note: "远期可选：深度解析与交叉验证（默认不部署）"},
 	}
 }

internal/ingest/ooxml_test.go

@@ -347,6 +347,7 @@ func TestParsersDescriptionMatchesDispatch(t *testing.T) {
 		"docx": "builtin:docx", "pdf": "builtin:pdf",
 		"xlsx": "builtin:xlsx", "xlsm": "builtin:xlsx",
 		"pptx": "builtin:pptx", "pptm": "builtin:pptx", "ppsx": "builtin:pptx",
+		"doc": "builtin:legacy-office", "xls": "builtin:legacy-office", "ppt": "builtin:legacy-office",
 	}
 	for ext, wantID := range check {
 		got, ok := byFormat[ext]
@@ -360,3 +361,72 @@ func TestParsersDescriptionMatchesDispatch(t *testing.T) {
 		}
 	}
 }
+
+// TestParseXlsxWideColumnSkipsCellNotSheets：稀疏样式单元格落在远端列（XFD 区，
+// 列序 ≥1024）只跳过该格并告警——不误报单元格上限、不丢弃后续工作表。
+func TestParseXlsxWideColumnSkipsCellNotSheets(t *testing.T) {
+	files := xlsxFixture()
+	// 第一表加一个列引用 XFD1（16384 列）的样式单元格；第二表（隐藏的"草稿"）必须照常解析。
+	files["xl/worksheets/sheet1.xml"] = strings.Replace(files["xl/worksheets/sheet1.xml"],
+		"</row>\n<row r=\"4\"", "</row>\n<row r=\"3\"><c r=\"XFD3\" t=\"inlineStr\"><is><t>边角样式</t></is></c></row>\n<row r=\"4\"", 1)
+	doc := Parse("宽表.xlsx", "", zipBytes(t, files))
+	heads := []string{}
+	for _, b := range doc.Blocks {
+		if b.Type == core.BlockHeading {
+			heads = append(heads, b.Text)
+		}
+	}
+	if strings.Join(heads, "|") != "报价|草稿（隐藏）" {
+		t.Fatalf("later sheets must survive a wide column: headings=%v warnings=%v", heads, doc.Warnings)
+	}
+	joined := strings.Join(doc.Warnings, ";")
+	if !strings.Contains(joined, "超过 1024 列") {
+		t.Fatalf("wide-column warning missing: %v", doc.Warnings)
+	}
+	if strings.Contains(joined, "单元格总数") {
+		t.Fatalf("cell-cap warning must not fire for a wide column: %v", doc.Warnings)
+	}
+	if doc.Meta.Confidence != 0.6 {
+		t.Fatalf("partial-content confidence expected 0.6: %v", doc.Meta.Confidence)
+	}
+	// 被跳过的远端列内容不得混进表格。
+	for _, b := range doc.Blocks {
+		if b.Type == core.BlockTable {
+			for _, row := range b.Rows {
+				for _, cell := range row {
+					if strings.Contains(cell, "边角样式") {
+						t.Fatalf("skipped wide-column cell leaked into table: %v", row)
+					}
+				}
+			}
+		}
+	}
+}
+
+// TestParseXlsxBadSheetXMLWarns：单张工作表 XML 损坏必须显式告警（其余表照常），
+// 与提案「显式失败，不静默」一致。
+func TestParseXlsxBadSheetXMLWarns(t *testing.T) {
+	files := xlsxFixture()
+	files["xl/worksheets/sheet1.xml"] = `<worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main"><sheetData><row`
+	doc := Parse("坏表.xlsx", "", zipBytes(t, files))
+	if len(doc.Warnings) == 0 {
+		t.Fatal("malformed sheet XML must warn")
+	}
+	joined := strings.Join(doc.Warnings, ";")
+	if !strings.Contains(joined, "工作表 报价") || !strings.Contains(joined, "XML 解码失败") {
+		t.Fatalf("warning should name the sheet and the failure: %v", doc.Warnings)
+	}
+	// 第二张表照常解析。
+	found := false
+	for _, b := range doc.Blocks {
+		if b.Type == core.BlockHeading && b.Text == "草稿（隐藏）" {
+			found = true
+		}
+	}
+	if !found {
+		t.Fatalf("healthy sheets must still parse: %+v", doc.Blocks)
+	}
+	if doc.Meta.Confidence != 0.6 {
+		t.Fatalf("partial parse confidence expected 0.6: %v", doc.Meta.Confidence)
+	}
+}

internal/ingest/xlsx.go

@@ -55,10 +55,16 @@ func parseXlsx(content []byte) ([]core.DocBlock, []string) {
 			warns = append(warns, fmt.Sprintf("工作表 %s 读取失败：%v", sh.Name, err))
 			continue
 		}
-		table, used, trunc := xlsxSheetBlocks(data, shared, dateStyles, date1904, cells)
+		table, used, trunc, wide, sheetWarn := xlsxSheetBlocks(data, shared, dateStyles, date1904, cells)
 		cells = used
+		if sheetWarn != "" {
+			warns = append(warns, fmt.Sprintf("工作表 %s：%s", sh.Name, sheetWarn))
+		}
+		if wide {
+			warns = append(warns, fmt.Sprintf("工作表 %s 含超过 %d 列的稀疏单元格，已跳过该列（其余内容不受影响）", sh.Name, xlsxMaxCols))
+		}
 		if table == nil {
-			continue // 空表
+			continue // 空表（读取失败/坏 XML 已单独告警）
 		}
 		title := sh.Name
 		if sh.State == "hidden" || sh.State == "veryHidden" {
@@ -264,20 +270,22 @@ type xlsxRowEl struct {
 	Cells []xlsxCellEl `xml:"c"`
 }
 
-// xlsxSheetBlocks 解析单张工作表；返回表格块、累计单元格数、是否触达上限。
-// 无内容行返回 nil 表。
-func xlsxSheetBlocks(data []byte, shared []string, dateStyles map[int]bool, date1904 bool, cellsUsed int) (*core.DocBlock, int, bool) {
+// xlsxSheetBlocks 解析单张工作表；返回表格块、累计单元格数、是否触达单元格
+// 上限、是否跳过超宽列、以及坏 XML 的告警（显式失败，不静默）。无内容行
+// 返回 nil 表。
+func xlsxSheetBlocks(data []byte, shared []string, dateStyles map[int]bool, date1904 bool, cellsUsed int) (*core.DocBlock, int, bool, bool, string) {
 	dec := xml.NewDecoder(bytes.NewReader(data))
 	var rows [][]string
 	count := cellsUsed
 	truncated := false
+	wide := false
 	for {
 		tok, err := dec.Token()
 		if err == io.EOF {
 			break
 		}
 		if err != nil {
-			return nil, count, false
+			return nil, count, truncated, wide, "XML 解码失败：" + err.Error()
 		}
 		st, ok := tok.(xml.StartElement)
 		if !ok || st.Name.Local != "row" {
@@ -300,7 +308,9 @@ func xlsxSheetBlocks(data []byte, shared []string, dateStyles map[int]bool, date
 				col = maxCol + 1 // 无引用：按出现顺序接续
 			}
 			if col >= xlsxMaxCols {
-				truncated = true
+				// 稀疏样式单元格常落在远端列（XFD 区）：跳过该格并告警，
+				// 不中断本表其余内容，也不阻断后续工作表。
+				wide = true
 				continue
 			}
 			cells[col] = xlsxCellText(c, shared, dateStyles, date1904)
@@ -323,9 +333,9 @@ func xlsxSheetBlocks(data []byte, shared []string, dateStyles map[int]bool, date
 		}
 	}
 	if len(rows) == 0 {
-		return nil, count, truncated
+		return nil, count, truncated, wide, ""
 	}
-	return &core.DocBlock{Type: core.BlockTable, Rows: rows}, count, truncated
+	return &core.DocBlock{Type: core.BlockTable, Rows: rows}, count, truncated, wide, ""
 }
 
 // xlsxCellText 把单元格转成展示文本。