Agent-System-Backend/internal/ingest/pptx.go

package ingest

// pptx/pptm/ppsx（PresentationML）内置解析器。幻灯片顺序取 presentation.xml
// 的 sldIdLst；标题占位符（title/ctrTitle）产标题块，正文形状按段落输出
//（a:br 换行），组合形状经同一 token 走查天然递归；mc:AlternateContent 只取
// Choice 分支；graphicFrame 内的表格按 tr/tc 输出（gridSpan/hMerge 占位保列
// 对齐）；备注页正文输出「备注：…」；页码/日期/页脚占位符跳过。图片与
// SmartArt 不解析。纯标准库。

import (
	"archive/zip"
	"bytes"
	"encoding/xml"
	"fmt"
	"io"
	"path"
	"strconv"
	"strings"

	core "agent-system-core"
)

func parsePptx(content []byte) ([]core.DocBlock, []string) {
	zr, err := openZip(content)
	if err != nil {
		return nil, []string{"pptx 解析失败：" + err.Error()}
	}
	slides, warns := pptxSlideOrder(zr)
	if slides == nil && len(warns) > 0 {
		return nil, warns
	}
	var blocks []core.DocBlock
	for i, sp := range slides {
		n := i + 1
		data, err := zipPart(zr, sp)
		if err != nil {
			warns = append(warns, fmt.Sprintf("幻灯片 %d 读取失败：%v", n, err))
			blocks = append(blocks, core.DocBlock{Type: core.BlockHeading, Level: 2, Text: fmt.Sprintf("幻灯片 %d", n)})
			continue
		}
		title, paras, tables := pptxSlideBlocks(data)
		heading := fmt.Sprintf("幻灯片 %d", n)
		if title != "" {
			heading += "：" + title
		}
		blocks = append(blocks, core.DocBlock{Type: core.BlockHeading, Level: 2, Text: heading})
		blocks = append(blocks, paras...)
		blocks = append(blocks, tables...)
		if note := pptxSlideNotes(zr, sp); note != "" {
			blocks = append(blocks, core.DocBlock{Type: core.BlockPara, Text: "备注：" + note})
		}
	}
	if len(blocks) == 0 && len(warns) == 0 {
		warns = append(warns, "pptx 无可解析的幻灯片内容")
	}
	return blocks, warns
}

// pptxSlideOrder 读 presentation.xml 的 sldIdLst → 幻灯片部件名（按顺序）。
func pptxSlideOrder(zr *zip.Reader) ([]string, []string) {
	data, err := zipPart(zr, "ppt/presentation.xml")
	if err != nil {
		return nil, []string{"pptx 解析失败：" + err.Error()}
	}
	rels, err := parseRels(zr, "ppt/presentation.xml")
	if err != nil {
		return nil, []string{"pptx 解析失败：" + err.Error()}
	}
	dec := xml.NewDecoder(bytes.NewReader(data))
	var out, warns []string
	for {
		tok, err := dec.Token()
		if err == io.EOF {
			break
		}
		if err != nil {
			return out, append(warns, "presentation.xml 解码失败："+err.Error())
		}
		st, ok := tok.(xml.StartElement)
		if !ok || st.Name.Local != "sldId" {
			continue
		}
		rel, ok := rels[ridAttr(st)]
		if !ok || !relIsType(rel, "/slide") {
			warns = append(warns, "幻灯片关系缺失或类型不符")
			continue
		}
		out = append(out, resolveRelTarget("ppt", rel.Target))
	}
	return out, warns
}

// pptxSlideBlocks 解析一张幻灯片：标题、正文段落、表格块。
// 表格块统一附在段落后（图形框与正文的精确穿插对检索无价值）。
func pptxSlideBlocks(data []byte) (title string, paras []core.DocBlock, tables []core.DocBlock) {
	dec := xml.NewDecoder(bytes.NewReader(data))
	var stack []string
	has := func(name string) bool {
		for _, s := range stack {
			if s == name {
				return true
			}
		}
		return false
	}
	skip := 0 // mc:Fallback 子树深度
	// 形状状态
	spDepth := -1
	phSkip := false
	isTitle := false
	var spParas []string
	var para strings.Builder
	paraOpen := false
	// 文本收集目标
	textInPara := false
	textInCell := false
	// 表格状态
	var tblRows [][]string
	var tblRow []string
	var cellBuf strings.Builder
	cellOpen := false
	gridSpan := 1
	cellHM := false

	finishPara := func() {
		if !paraOpen {
			return
		}
		paraOpen = false
		if s := strings.TrimRight(para.String(), "\n"); strings.TrimSpace(s) != "" {
			spParas = append(spParas, strings.TrimSpace(s))
		}
		para.Reset()
	}

	for {
		tok, err := dec.Token()
		if err == io.EOF {
			break
		}
		if err != nil {
			return "", paras, tables
		}
		switch t := tok.(type) {
		case xml.StartElement:
			if skip > 0 {
				skip++
				continue
			}
			local := t.Name.Local
			switch local {
			case "Fallback":
				if has("AlternateContent") {
					skip = 1
					continue
				}
			case "sp":
				spDepth = len(stack)
				phSkip, isTitle, spParas = false, false, nil
			case "ph":
				if spDepth >= 0 && len(stack) > spDepth {
					switch attrLocal(t, "type") {
					case "title", "ctrTitle":
						isTitle = true
					case "dt", "ftr", "sldNum":
						phSkip = true
					}
				}
			case "p":
				if spDepth >= 0 && has("txBody") && !has("tbl") {
					finishPara()
					paraOpen = true
					para.Reset()
				} else if cellOpen {
					if cellBuf.Len() > 0 {
						cellBuf.WriteByte('\n')
					}
				}
			case "br":
				if paraOpen {
					para.WriteByte('\n')
				}
			case "t":
				if has("fld") {
					break // 字段（页码/日期）不取
				}
				textInPara = paraOpen
				textInCell = cellOpen && !paraOpen
			case "tc":
				if has("tbl") {
					cellBuf.Reset()
					cellOpen = true
					gridSpan, _ = strconv.Atoi(attrLocal(t, "gridSpan"))
					if gridSpan < 1 {
						gridSpan = 1
					}
					hm := attrLocal(t, "hMerge")
					cellHM = hm == "1" || strings.EqualFold(hm, "true")
				}
			}
			stack = append(stack, local)
		case xml.CharData:
			if textInPara {
				para.Write(t)
			} else if textInCell {
				cellBuf.Write(t)
			}
		case xml.EndElement:
			if skip > 0 {
				skip--
				continue
			}
			if len(stack) > 0 {
				stack = stack[:len(stack)-1]
			}
			switch t.Name.Local {
			case "t":
				textInPara, textInCell = false, false
			case "p":
				finishPara()
			case "sp":
				if spDepth >= 0 && len(stack) == spDepth {
					if !phSkip && len(spParas) > 0 {
						if isTitle && title == "" {
							title = strings.Join(spParas, " ")
						} else {
							for _, p := range spParas {
								paras = append(paras, core.DocBlock{Type: core.BlockPara, Text: p})
							}
						}
					}
					spDepth = -1
					phSkip, isTitle, spParas = false, false, nil
				}
			case "tc":
				if cellOpen {
					text := strings.TrimSpace(cellBuf.String())
					if cellHM {
						text = "" // 横向合并的续格：占位保列对齐
					}
					tblRow = append(tblRow, text)
					for i := 1; i < gridSpan; i++ {
						tblRow = append(tblRow, "") // 合并占位保列对齐
					}
					cellOpen = false
				}
			case "tr":
				if len(tblRow) > 0 {
					for len(tblRow) > 0 && tblRow[len(tblRow)-1] == "" {
						tblRow = tblRow[:len(tblRow)-1]
					}
					if len(tblRow) > 0 {
						tblRows = append(tblRows, tblRow)
					}
					tblRow = nil
				}
			case "tbl":
				if len(tblRows) > 0 {
					tables = append(tables, core.DocBlock{Type: core.BlockTable, Rows: tblRows})
				}
				tblRows = nil
			}
		}
	}
	finishPara()
	return title, paras, tables
}

// pptxSlideNotes 读幻灯片的备注页正文；无备注返回空串。
func pptxSlideNotes(zr *zip.Reader, slidePart string) string {
	rels, err := parseRels(zr, slidePart)
	if err != nil {
		return ""
	}
	for _, rel := range rels {
		if !relIsType(rel, "/notesSlide") {
			continue
		}
		data, err := zipPart(zr, resolveRelTarget(path.Dir(slidePart), rel.Target))
		if err != nil {
			return ""
		}
		_, paras, _ := pptxSlideBlocks(data)
		var lines []string
		for _, p := range paras {
			lines = append(lines, p.Text)
		}
		return strings.Join(lines, "\n")
	}
	return ""
}