feat(search): index embedded PDF attachment text (#42)

testdata/pdf-with-attachment.pdf

@@ -0,0 +1,114 @@
+%PDF-1.7
+%Çì�¢
+%%Invocation: gs -q -dNOPAUSE -dBATCH -sDEVICE=pdfwrite ? ? ?
+5 0 obj
+<</Length 6 0 R/Filter /FlateDecode>>
+stream
+xœ-ŠA
+ƒ0÷ÿoÙnìO7q]èZ*ÿ�IˆmJ½½M
+³f7
+\¨6‘žfRÿŠ*ñºõª…8:g}‡f†Dºø”ÞiØsúØ	ÝôÝ;炱(Ùn.ly]ìUFz
+½~Aë øendstream
+endobj
+6 0 obj
+110
+endobj
+4 0 obj
+<</Type/Page/MediaBox [0 0 612 792]
+/Rotate 0/Parent 3 0 R
+/Resources<</ProcSet[/PDF /Text]
+/Font 8 0 R
+>>
+/Contents 5 0 R
+>>
+endobj
+3 0 obj
+<< /Type /Pages /Kids [
+4 0 R
+] /Count 1
+>>
+endobj
+1 0 obj
+<</Type /Catalog /Pages 3 0 R
+/Metadata 9 0 R
+>>
+endobj
+8 0 obj
+<</R7
+7 0 R>>
+endobj
+7 0 obj
+<</BaseFont/Helvetica/Type/Font
+/Subtype/Type1>>
+endobj
+9 0 obj
+<</Type/Metadata
+/Subtype/XML/Length 1173>>stream
+<?xpacket begin='' id='W5M0MpCehiHzreSzNTczkc9d'?>
+<?adobe-xap-filters esc="CRLF"?>
+<x:xmpmeta xmlns:x='adobe:ns:meta/' x:xmptk='XMP toolkit 2.9.1-13, framework 1.6'>
+<rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#' xmlns:iX='http://ns.adobe.com/iX/1.0/'>
+<rdf:Description rdf:about="" xmlns:pdf='http://ns.adobe.com/pdf/1.3/' pdf:Producer='GPL Ghostscript 10.02.1'/>
+<rdf:Description rdf:about="" xmlns:xmp='http://ns.adobe.com/xap/1.0/'><xmp:ModifyDate>2026-09-16T17:29:12Z</xmp:ModifyDate>
+<xmp:CreateDate>2026-09-16T17:29:12Z</xmp:CreateDate>
+<xmp:CreatorTool>UnknownApplication</xmp:CreatorTool></rdf:Description>
+<rdf:Description rdf:about="" xmlns:xapMM='http://ns.adobe.com/xap/1.0/mm/' xapMM:DocumentID='uuid:ae8d7575-ea10-11fc-0000-3a98742e0b71'/>
+<rdf:Description rdf:about="" xmlns:dc='http://purl.org/dc/elements/1.1/' dc:format='application/pdf'><dc:title><rdf:Alt><rdf:li xml:lang='x-default'>Untitled</rdf:li></rdf:Alt></dc:title></rdf:Description>
+</rdf:RDF>
+</x:xmpmeta>
+                                                                        
+                                                                        
+<?xpacket end='w'?>
+endstream
+endobj
+2 0 obj
+<</Producer(GPL Ghostscript 10.02.1)
+/CreationDate(D:20260916172912Z00'00')
+/ModDate(D:20260916172912Z00'00')>>endobj
+xref
+0 10
+0000000000 65535 f 
+0000000476 00000 n 
+0000001882 00000 n 
+0000000417 00000 n 
+0000000276 00000 n 
+0000000077 00000 n 
+0000000257 00000 n 
+0000000569 00000 n 
+0000000540 00000 n 
+0000000633 00000 n 
+trailer
+<< /Size 10 /Root 1 0 R /Info 2 0 R
+/ID [<5A562476FBF11852133AA873452909F9><5A562476FBF11852133AA873452909F9>]
+>>
+startxref
+2008
+%%EOF
+1 0 obj
+<</Type /Catalog /Pages 3 0 R /Metadata 9 0 R /Names <</EmbeddedFiles 12 0 R >> >> 
+endobj
+10 0 obj
+<</Length 44 /Params <</Size 44 >> >> stream
+gooattachmenttoken embedded attachment text
+
+endstream
+
+endobj
+11 0 obj
+<</Type /Filespec /UF <feff0067006f006f002d006e006f00740065002e007400780074> /EF <</F 10 0 R >> >> 
+endobj
+12 0 obj
+<</Names [<feff0067006f006f002d006e006f00740065002e007400780074> 11 0 R ] >> 
+endobj
+xref
+0 2
+0000000002 65535 f
+0000002361 00000 n
+10 3
+0000002463 00000 n
+0000002586 00000 n
+0000002705 00000 n
+trailer
+<</Size 13 /ID [(ZV$vûñR:¨sE\)	ù) (P…õrˆ‚ Åð¡Ï) ] /Root 1 0 R /Prev 2008 /Info 2 0 R >> 
+startxref
+2802