fix(text): complete Adobe Glyph List mapping in glyph_name_to_unicode for /Differences font encodings #572

// Cargo.toml dependencies:
// oxidize-pdf = "5.0.1"
// lopdf = "0.34.0"

use lopdf::content::{Content, Operation};
use lopdf::{Document, Object, Stream, dictionary};
use oxidize_pdf::parser::PdfReader;
use oxidize_pdf::text::TextExtractor;

fn generate_type1_differences_pdf() -> Vec<u8> {
    let mut doc = Document::with_version("1.5");
    let pages_id = doc.new_object_id();

    // /Encoding dictionary mapping bytes 1..5 to glyph names /plus, /T, /e, /s, /t
    let enc_dict = dictionary! {
        "Type" => "Encoding",
        "BaseEncoding" => "WinAnsiEncoding",
        "Differences" => Object::Array(vec![
            Object::Integer(1),
            Object::Name(b"plus".to_vec()),
            Object::Name(b"T".to_vec()),
            Object::Name(b"e".to_vec()),
            Object::Name(b"s".to_vec()),
            Object::Name(b"t".to_vec()),
        ]),
    };
    let enc_id = doc.add_object(enc_dict);
    let font_id = doc.add_object(dictionary! {
        "Type" => "Font",
        "Subtype" => "Type1",
        "BaseFont" => "Helvetica",
        "Encoding" => enc_id,
    });
    let res_id = doc.add_object(dictionary! {
        "Font" => dictionary! { "F1" => font_id },
    });

    // Content stream showing byte sequence [1, 2, 3, 4, 5]
    let content = Content {
        operations: vec![
            Operation::new("BT", vec![]),
            Operation::new("Tf", vec![Object::Name(b"F1".to_vec()), Object::Integer(12)]),
            Operation::new("Tj", vec![Object::String(vec![1, 2, 3, 4, 5], lopdf::StringFormat::Literal)]),
            Operation::new("ET", vec![]),
        ],
    };
    let content_id = doc.add_object(Stream::new(dictionary! {}, content.encode().unwrap()));
    let page_id = doc.add_object(dictionary! {
        "Type" => "Page",
        "Parent" => pages_id,
        "Contents" => content_id,
        "Resources" => res_id,
    });
    doc.objects.insert(pages_id, Object::Dictionary(dictionary! {
        "Type" => "Pages",
        "Kids" => Object::Array(vec![Object::Reference(page_id)]),
        "Count" => 1_i64,
        "MediaBox" => Object::Array(vec![0.into(), 0.into(), 595.into(), 842.into()]),
    }));
    let cat_id = doc.add_object(dictionary! { "Type" => "Catalog", "Pages" => pages_id });
    doc.trailer.set("Root", cat_id);

    let mut bytes = Vec::new();
    doc.save_to(&mut bytes).unwrap();
    bytes
}

fn main() {
    let pdf_bytes = generate_type1_differences_pdf();
    let reader = PdfReader::new(std::io::Cursor::new(pdf_bytes)).unwrap();
    let doc = reader.into_document();

    let mut extractor = TextExtractor::new();
    let page = extractor.extract_from_page(&doc, 0).unwrap();

    println!("Extracted text: {:?}", page.text);
    // Expected: "+Test"
    // Actual:   "+" (because 'e', 's', 't' are not mapped in glyph_name_to_unicode and get stripped)
    assert_eq!(page.text.trim(), "+Test");
}