mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-09 12:32:52 +00:00
M3: vertical Latin widths come from /DW and are looked up by CID, and close columns stay apart (view.find)
Tests only: a CID missing from /W is /DW wide across the column (ISO 32000-2 §9.7.4.3), widths are looked up by CID through an embedded vertical CMap, and two columns of /DW-wide letters set 13.5 pt apart at 20 pt read as two lines. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Pq7HyCHD1R3rywQBPCHXZA
This commit is contained in:
mtlcl410andClaude Opus 5.5 committed
1 parent
118691e9b7
commit
65b7324c02
1 file changed
+76
-27
@@ -589,33 +589,11 @@ fn horizontally_scaled_vertical_latin_box_is_scaled_across_the_column() {
|
||||
|
||||
/// `ABCDE` down one Identity-V column at 24 pt with `tc Tc` and `tz Tz`.
|
||||
fn tracked_vertical_latin(tc: f32, tz: f32) {
|
||||
use lopdf::{Document, Object, Stream, dictionary};
|
||||
let mut doc = Document::with_version("1.7");
|
||||
let cmap = b"/CIDInit /ProcSet findresource begin 12 dict begin begincmap /CIDSystemInfo << /Registry (Adobe) /Ordering (UCS) /Supplement 0 >> def /CMapName /TestUnicode def /CMapType 2 def 1 begincodespacerange <0000> <FFFF> endcodespacerange 5 beginbfchar <0024> <0041> <0025> <0042> <0026> <0043> <0027> <0044> <0028> <0045> endbfchar endcmap CMapName currentdict /CMap defineresource pop end end";
|
||||
let unicode = doc.add_object(Stream::new(dictionary! {}, cmap.to_vec()));
|
||||
let widths: Vec<Object> = [(36, 667), (37, 667), (38, 722), (39, 722), (40, 667)]
|
||||
.into_iter()
|
||||
.flat_map(|(cid, w)| [Object::Integer(cid), Object::Array(vec![Object::Integer(w)])])
|
||||
.collect();
|
||||
let cid = doc.add_object(dictionary! {
|
||||
"Type" => "Font", "Subtype" => "CIDFontType2", "BaseFont" => "TestVerticalLatin",
|
||||
"CIDSystemInfo" => dictionary! { "Registry" => Object::string_literal("Adobe"), "Ordering" => Object::string_literal("Identity"), "Supplement" => 0 },
|
||||
"DW" => 1000, "W" => widths, "DW2" => vec![Object::Integer(880), Object::Integer(-1000)], "CIDToGIDMap" => "Identity"
|
||||
});
|
||||
let font = doc.add_object(dictionary! { "Type" => "Font", "Subtype" => "Type0", "BaseFont" => "TestVerticalLatin", "Encoding" => "Identity-V", "DescendantFonts" => vec![Object::Reference(cid)], "ToUnicode" => unicode });
|
||||
let content = doc.add_object(Stream::new(
|
||||
dictionary! {},
|
||||
format!("BT /F1 24 Tf {tc} Tc {tz} Tz 1 0 0 1 100 340 Tm <00240025002600270028> Tj ET").into_bytes(),
|
||||
));
|
||||
let pages = doc.new_object_id();
|
||||
let page = doc.add_object(dictionary! { "Type" => "Page", "Parent" => pages, "MediaBox" => vec![Object::Integer(0), Object::Integer(0), Object::Integer(400), Object::Integer(500)], "Resources" => dictionary! {"Font" => dictionary! {"F1" => font}}, "Contents" => content });
|
||||
doc.objects.insert(pages, dictionary! {"Type" => "Pages", "Kids" => vec![Object::Reference(page)], "Count" => 1}.into());
|
||||
let catalog = doc.add_object(dictionary! {"Type" => "Catalog", "Pages" => pages});
|
||||
doc.trailer.set("Root", catalog);
|
||||
let mut bytes = Vec::new();
|
||||
doc.save_to(&mut bytes).unwrap();
|
||||
let pdf = Pdf::new(std::sync::Arc::new(bytes)).unwrap();
|
||||
let text = extract_page(&pdf, 0, &InterpreterSettings::default()).unwrap();
|
||||
let text = vertical_latin(
|
||||
&[(36, 667), (37, 667), (38, 722), (39, 722), (40, 667)],
|
||||
None,
|
||||
&format!("BT /F1 24 Tf {tc} Tc {tz} Tz 1 0 0 1 100 340 Tm <00240025002600270028> Tj ET"),
|
||||
);
|
||||
assert_eq!(text.plain_text(), "ABCDE");
|
||||
assert_eq!(text.find("ABCDE"), vec![0..5]);
|
||||
// Each box spans w0 (here 24 pt × 0.667 or 0.722, times Th) centred on the column at x = 100.
|
||||
@@ -627,6 +605,77 @@ fn tracked_vertical_latin(tc: f32, tz: f32) {
|
||||
}
|
||||
}
|
||||
|
||||
/// The text of a page showing `content` in a vertical CIDFontType2 `/F1` with `/DW 1000`, the
|
||||
/// `widths` (CID, w0) in `/W`, and CIDs 36 to 41 reading `A` to `F`. `cmap` is the body of an
|
||||
/// embedded vertical CMap mapping codes to CIDs (`begincidchar` … `endcidchar`); `None` uses
|
||||
/// Identity-V.
|
||||
fn vertical_latin(widths: &[(i64, i64)], cmap: Option<&str>, content: &str) -> crate::text::PageText {
|
||||
use lopdf::{Document, Object, Stream, dictionary};
|
||||
let mut doc = Document::with_version("1.7");
|
||||
let to_unicode = b"/CIDInit /ProcSet findresource begin 12 dict begin begincmap /CIDSystemInfo << /Registry (Adobe) /Ordering (UCS) /Supplement 0 >> def /CMapName /TestUnicode def /CMapType 2 def 1 begincodespacerange <0000> <FFFF> endcodespacerange 6 beginbfchar <0024> <0041> <0025> <0042> <0026> <0043> <0027> <0044> <0028> <0045> <0029> <0046> endbfchar endcmap CMapName currentdict /CMap defineresource pop end end";
|
||||
let unicode = doc.add_object(Stream::new(dictionary! {}, to_unicode.to_vec()));
|
||||
let widths: Vec<Object> = widths.iter().flat_map(|&(cid, w)| [Object::Integer(cid), Object::Array(vec![Object::Integer(w)])]).collect();
|
||||
let cid = doc.add_object(dictionary! {
|
||||
"Type" => "Font", "Subtype" => "CIDFontType2", "BaseFont" => "TestVerticalLatin",
|
||||
"CIDSystemInfo" => dictionary! { "Registry" => Object::string_literal("Adobe"), "Ordering" => Object::string_literal("Identity"), "Supplement" => 0 },
|
||||
"DW" => 1000, "W" => widths, "DW2" => vec![Object::Integer(880), Object::Integer(-1000)], "CIDToGIDMap" => "Identity"
|
||||
});
|
||||
let encoding = match cmap {
|
||||
Some(body) => {
|
||||
let stream = format!(
|
||||
"/CIDInit /ProcSet findresource begin 12 dict begin begincmap /CIDSystemInfo << /Registry (Adobe) /Ordering (Identity) /Supplement 0 >> def /CMapName /TestCodes-V def /CMapType 1 def /WMode 1 def 1 begincodespacerange <0000> <FFFF> endcodespacerange {body} endcmap CMapName currentdict /CMap defineresource pop end end"
|
||||
);
|
||||
Object::Reference(doc.add_object(Stream::new(
|
||||
dictionary! { "Type" => "CMap", "CMapName" => "TestCodes-V", "WMode" => 1, "CIDSystemInfo" => dictionary! { "Registry" => Object::string_literal("Adobe"), "Ordering" => Object::string_literal("Identity"), "Supplement" => 0 } },
|
||||
stream.into_bytes(),
|
||||
)))
|
||||
}
|
||||
None => Object::Name(b"Identity-V".to_vec()),
|
||||
};
|
||||
let font = doc.add_object(dictionary! { "Type" => "Font", "Subtype" => "Type0", "BaseFont" => "TestVerticalLatin", "Encoding" => encoding, "DescendantFonts" => vec![Object::Reference(cid)], "ToUnicode" => unicode });
|
||||
let content = doc.add_object(Stream::new(dictionary! {}, content.as_bytes().to_vec()));
|
||||
let pages = doc.new_object_id();
|
||||
let page = doc.add_object(dictionary! { "Type" => "Page", "Parent" => pages, "MediaBox" => vec![Object::Integer(0), Object::Integer(0), Object::Integer(400), Object::Integer(500)], "Resources" => dictionary! {"Font" => dictionary! {"F1" => font}}, "Contents" => content });
|
||||
doc.objects.insert(pages, dictionary! {"Type" => "Pages", "Kids" => vec![Object::Reference(page)], "Count" => 1}.into());
|
||||
let catalog = doc.add_object(dictionary! {"Type" => "Catalog", "Pages" => pages});
|
||||
doc.trailer.set("Root", catalog);
|
||||
let mut bytes = Vec::new();
|
||||
doc.save_to(&mut bytes).unwrap();
|
||||
let pdf = Pdf::new(std::sync::Arc::new(bytes)).unwrap();
|
||||
extract_page(&pdf, 0, &InterpreterSettings::default()).unwrap()
|
||||
}
|
||||
|
||||
/// A CID that `/W` doesn't list is `/DW` wide across the column (ISO 32000-2 §9.7.4.3), and the
|
||||
/// widths are looked up by CID, not by character code: an embedded vertical CMap maps the codes
|
||||
/// `<0024>`… (which `/W` lists 500 wide as CIDs) to CIDs 50…. The tracked column stays one line
|
||||
/// that Find matches.
|
||||
#[test]
|
||||
fn vertical_latin_widths_come_from_dw_and_are_looked_up_by_cid() {
|
||||
let cmap = "5 begincidchar <0024> 50 <0025> 51 <0026> 52 <0027> 53 <0028> 54 endcidchar";
|
||||
// CID 52 (`C`) has no /W entry: it is /DW = 1000 wide.
|
||||
let widths = [(36, 500), (37, 500), (38, 500), (39, 500), (40, 500), (50, 667), (51, 667), (53, 722), (54, 667)];
|
||||
let text = vertical_latin(&widths, Some(cmap), "BT /F1 24 Tf -40 Tc 1 0 0 1 100 340 Tm <00240025002600270028> Tj ET");
|
||||
assert_eq!(text.plain_text(), "ABCDE");
|
||||
assert_eq!(text.find("ABCDE"), vec![0..5]);
|
||||
let got: Vec<f32> = text.glyphs.iter().map(|g| g.rect[2] - g.rect[0]).collect();
|
||||
assert_eq!(got.len(), 5);
|
||||
for (w, w0) in got.iter().zip([667.0, 667.0, 1000.0, 722.0, 667.0]) {
|
||||
assert!((w - 24.0 * w0 / 1000.0).abs() < 0.01, "{got:?}");
|
||||
}
|
||||
}
|
||||
|
||||
/// Two vertical columns of `/DW`-wide letters set 13.5 pt apart at 20 pt overlap across the
|
||||
/// column (each box is 20 pt wide), and still read as two lines, in order, with Find matching
|
||||
/// each column and not a word spanning both.
|
||||
#[test]
|
||||
fn close_vertical_columns_of_dw_wide_letters_stay_apart() {
|
||||
let text = vertical_latin(&[], None, "BT /F1 20 Tf 1 0 0 1 113.5 340 Tm <002400250026> Tj 1 0 0 1 100 340 Tm <002700280029> Tj ET");
|
||||
assert_eq!(text.plain_text().lines().map(str::trim).collect::<Vec<_>>(), ["ABC", "DEF"]);
|
||||
assert_eq!(text.find("ABC").len(), 1);
|
||||
assert_eq!(text.find("DEF").len(), 1);
|
||||
assert!(text.find("CD").is_empty() && text.find("ABCDEF").is_empty(), "{:?}", text.plain_text());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn upright_mapping_round_trips() {
|
||||
let r = [10.0, 20.0, 30.0, 25.0];
|
||||
|
||||
Reference in new issue
Block a user