feat: index the text of attached PDFs

- jz_bm_material_file_texts caches the pdftotext output per file
- the River job jz.bm.extract_material_text extracts and resyncs
- the management multipart attach queues it inside its transaction
- file_texts in the document and a file snippet with its name

internal/pdftest/pdf.go

@@ -0,0 +1,42 @@
+// Package pdftest builds small PDFs for the jz.bm tests. Only tests import
+// it.
+package pdftest
+
+import (
+	"bytes"
+	"fmt"
+	"strings"
+)
+
+// OnePage is a one-page PDF that shows text in the base-14 Helvetica font,
+// so pdftotext extracts it without any embedded font. text must be ASCII
+// and hold no parentheses or backslashes. The xref offsets are computed from
+// the objects as written.
+func OnePage(text string) []byte {
+	if strings.ContainsAny(text, "()\\") {
+		panic("pdftest: text holds a parenthesis or a backslash")
+	}
+	stream := "BT /F1 24 Tf 72 700 Td (" + text + ") Tj ET"
+	objects := []string{
+		"<< /Type /Catalog /Pages 2 0 R >>",
+		"<< /Type /Pages /Kids [3 0 R] /Count 1 >>",
+		"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>",
+		fmt.Sprintf("<< /Length %d >>\nstream\n%s\nendstream", len(stream), stream),
+		"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>",
+	}
+	var b bytes.Buffer
+	b.WriteString("%PDF-1.4\n")
+	offsets := make([]int, len(objects))
+	for i, obj := range objects {
+		offsets[i] = b.Len()
+		fmt.Fprintf(&b, "%d 0 obj\n%s\nendobj\n", i+1, obj)
+	}
+	xref := b.Len()
+	fmt.Fprintf(&b, "xref\n0 %d\n", len(objects)+1)
+	b.WriteString("0000000000 65535 f \n")
+	for _, off := range offsets {
+		fmt.Fprintf(&b, "%010d 00000 n \n", off)
+	}
+	fmt.Fprintf(&b, "trailer\n<< /Size %d /Root 1 0 R >>\nstartxref\n%d\n%%%%EOF\n", len(objects)+1, xref)
+	return b.Bytes()
+}