feat(extract): implement PDF extraction via pdftotext

ingestion/internal/extract/pdf.go

@@ -1,8 +1,28 @@
 // ingestion/internal/extract/pdf.go
 package extract
 
-import "fmt"
+import (
+	"bytes"
+	"fmt"
+	"os/exec"
+	"strings"
+)
 
-func extractPDF(_ string) (string, error) {
-	return "", fmt.Errorf("PDF extraction not implemented")
+// extractPDF runs pdftotext on path and returns the extracted text.
+// pdftotext must be installed (package: poppler-utils on Alpine/Debian, poppler on Homebrew).
+func extractPDF(path string) (string, error) {
+	cmd := exec.Command("pdftotext", "-q", path, "-")
+	var stdout, stderr bytes.Buffer
+	cmd.Stdout = &stdout
+	cmd.Stderr = &stderr
+
+	if err := cmd.Run(); err != nil {
+		errMsg := strings.TrimSpace(stderr.String())
+		if errMsg == "" {
+			errMsg = err.Error()
+		}
+		return "", fmt.Errorf("pdftotext: %s", errMsg)
+	}
+
+	return strings.TrimSpace(stdout.String()), nil
 }