mirror of
https://pdfium.googlesource.com/pdfium
synced 2026-07-30 10:21:46 +08:00
Distill the PDF attached on the bug into a minimal test case. Add an embedder test case to extract the text. Show that the text is missing a dash. Bug: 431824298 Change-Id: I67ce45a17dca191e28a7aa31e9b27cbe339b37b2 Reviewed-on: https://pdfium-review.googlesource.com/c/pdfium/+/134450 Reviewed-by: Tom Sepez <tsepez@chromium.org> Commit-Queue: Lei Zhang <thestig@chromium.org>
119 lines
1.6 KiB
Plaintext
119 lines
1.6 KiB
Plaintext
{{header}}
|
|
{{object 1 0}} <<
|
|
/Type /Catalog
|
|
/Pages 2 0 R
|
|
>>
|
|
endobj
|
|
{{object 2 0}} <<
|
|
/Type /Pages
|
|
/Count 1
|
|
/Kids [3 0 R]
|
|
>>
|
|
endobj
|
|
{{object 3 0}} <<
|
|
/Type /Page
|
|
/Parent 2 0 R
|
|
/Contents 4 0 R
|
|
/MediaBox [0 0 200 300]
|
|
/Resources <<
|
|
/Font <<
|
|
/F1 5 0 R
|
|
/F2 6 0 R
|
|
>>
|
|
>>
|
|
>>
|
|
endobj
|
|
{{object 4 0}} <<
|
|
{{streamlen}}
|
|
>>
|
|
stream
|
|
BT
|
|
/F1 12 Tf
|
|
20 80 Td
|
|
[(-hello-)] TJ
|
|
ET
|
|
BT
|
|
/F1 12 Tf
|
|
20 50 Td
|
|
[(-world-)] TJ
|
|
ET
|
|
BT
|
|
/F2 12 Tf
|
|
20 30 Td
|
|
[<064F216E>] TJ
|
|
ET
|
|
endstream
|
|
endobj
|
|
{{object 5 0}} <<
|
|
/Type /Font
|
|
/Subtype /Type1
|
|
/BaseFont /Helvetica
|
|
>>
|
|
endobj
|
|
{{object 6 0}} <<
|
|
/Type /Font
|
|
/Subtype /Type0
|
|
/BaseFont /BCDEEE+SimSun
|
|
/DescendantFonts [7 0 R]
|
|
/Encoding /Identity-H
|
|
/ToUnicode 9 0 R
|
|
>>
|
|
endobj
|
|
{{object 7 0}} <<
|
|
/Type /Font
|
|
/Subtype /CIDFontType2
|
|
/BaseFont /BCDEEE+SimSun
|
|
/CIDToGIDMap /Identity
|
|
/DW 1000
|
|
/FontDescriptor 8 0 R
|
|
>>
|
|
endobj
|
|
{{object 8 0}} <<
|
|
/Type /FontDescriptor
|
|
/Ascent 859
|
|
/AvgWidth 500
|
|
/CapHeight 859
|
|
/Descent -141
|
|
/Flags 32
|
|
/FontBBox [-8 -141 1000 859]
|
|
/FontName /BCDEEE+SimSun
|
|
/FontWeight 400
|
|
/ItalicAngle 0
|
|
/Leading 141
|
|
/MaxWidth 1008
|
|
/StemV 50
|
|
/XHeight 250
|
|
>>
|
|
endobj
|
|
{{object 9 0}} <<
|
|
{{streamlen}}
|
|
>>
|
|
stream
|
|
/CIDInit /ProcSet findresource begin
|
|
28 dict begin
|
|
begincmap
|
|
/CIDSystemInfo <<
|
|
/Registry (Adobe)
|
|
/Ordering (UCS)
|
|
/Supplement 0
|
|
>> def
|
|
/CMapName /Adobe-Identity-UCS def
|
|
/CMapType 2 def
|
|
1 begincodespacerange
|
|
<0000> <FFFF>
|
|
endcodespacerange
|
|
2 beginbfchar
|
|
<064F> <501F>
|
|
<216E> <6B3E>
|
|
endbfchar
|
|
endcmap
|
|
CMapName currentdict /CMap defineresource pop
|
|
end
|
|
end
|
|
endstream
|
|
endobj
|
|
{{xref}}
|
|
{{trailer}}
|
|
{{startxref}}
|
|
%%EOF
|