Apply JPEG EXIF orientation when creating PDFs from images (#2951)

Fixes #2944

Co-authored-by: Claude Haiku 5.5 <noreply@anthropic.com>

crates/create/src/lib.rs

@@ -5,6 +5,7 @@
 use pdfcraft_cos::{Dict, Document, ObjRef, Object, PdfString, Stream};
 
 mod extract;
+mod upright_image;
 pub use extract::{ExtractedImage, ImageExport, extract_images, image_file};
 use pdfcraft_fonts::{literal, win_ansi, wrap};
 
@@ -528,7 +529,7 @@ pub fn source_kind(name: &str, bytes: &[u8]) -> Option<SourceKind> {
 /// Detect the image format from its bytes; a TIFF may hold several pages.
 fn embed(name: &str, bytes: &[u8]) -> Result<Vec<Embedded>, CreateError> {
     if bytes.starts_with(&[0xFF, 0xD8]) {
-        Ok(vec![jpeg(name, bytes)?])
+        Ok(vec![jpeg(name, &upright_image::upright(bytes))?])
     } else if bytes.starts_with(b"\x89PNG\r\n\x1a\n") {
         Ok(vec![png_image(name, bytes)?])
     } else if is_tiff(bytes) {

crates/create/src/tests.rs

@@ -949,3 +949,36 @@ fn cmyk_and_ycck_jpegs_export_in_the_colours_the_page_shows() {
         }
     }
 }
+
+/// A 60 x 20 JPEG at `dpi` x 72 dpi, tagged with EXIF `orientation` (6: shown turned 90 degrees
+/// clockwise).
+pub(crate) fn phone_jpeg(orientation: u8, dpi: u16) -> Vec<u8> {
+    use image::codecs::jpeg::{JpegEncoder, PixelDensity, PixelDensityUnit};
+    let mut jpeg = Vec::new();
+    let mut encoder = JpegEncoder::new(&mut jpeg);
+    encoder.set_pixel_density(PixelDensity { density: (dpi, 72), unit: PixelDensityUnit::Inches });
+    encoder.encode_image(&image::RgbImage::from_pixel(60, 20, image::Rgb([20, 20, 20]))).unwrap();
+    let mut exif = b"Exif\0\0II\x2a\0\x08\0\0\0\x01\0\x12\x01\x03\0\x01\0\0\0".to_vec();
+    exif.extend_from_slice(&[orientation, 0, 0, 0, 0, 0, 0, 0]);
+    let mut out = jpeg[..2].to_vec();
+    out.extend_from_slice(&[0xff, 0xe1]);
+    out.extend_from_slice(&((exif.len() + 2) as u16).to_be_bytes());
+    out.extend_from_slice(&exif);
+    out.extend_from_slice(&jpeg[2..]);
+    out
+}
+
+#[test]
+fn a_jpeg_with_an_exif_orientation_becomes_an_upright_page() {
+    let doc = reopen(&from_images(&[("photo.jpg".into(), phone_jpeg(6, 144)), ("plain.jpg".into(), phone_jpeg(1, 72))]).unwrap());
+    // Stored 60 x 20 px at 144 x 72 dpi; turned it is 20 x 60 px at 72 x 144 dpi: 20 x 30 pt.
+    let m0 = media(&pages(&doc)[0]);
+    assert!((m0[2] - 20.0).abs() < 0.01 && (m0[3] - 30.0).abs() < 0.01, "{m0:?}");
+    let img = image_of(&doc, 0);
+    assert_eq!((img.int(b"Width"), img.int(b"Height")), (Some(20), Some(60)));
+    // "As stored" stays as it is.
+    let m1 = media(&pages(&doc)[1]);
+    assert!((m1[2] - 60.0).abs() < 0.01 && (m1[3] - 20.0).abs() < 0.01, "{m1:?}");
+    let img = image_of(&doc, 1);
+    assert_eq!((img.int(b"Width"), img.int(b"Height")), (Some(60), Some(20)));
+}

crates/create/src/upright_image.rs

@@ -1,6 +1,6 @@
 //! Photos from phones are stored sideways with an EXIF Orientation tag. PDF image XObjects have
-//! no such tag, so a JPEG embedded as it is would show up turned. Images placed into a page
-//! (stamps, added images, replacements) go through here first.
+//! no such tag, so a JPEG embedded as it is would show up turned. Every JPEG embedded by this
+//! crate (pages made from images, stamps, added images, replacements) goes through here first.
 
 use std::borrow::Cow;
 use std::io::Cursor;
@@ -79,24 +79,7 @@ fn jfif_density(bytes: &[u8]) -> Option<PixelDensity> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::{Edit, MarkFile};
-
-    /// A 60 x 20 JPEG at `dpi` x 72 dpi, tagged with EXIF `orientation` (6: shown turned 90
-    /// degrees clockwise).
-    fn phone_jpeg(orientation: u8, dpi: u16) -> Vec<u8> {
-        let mut jpeg = Vec::new();
-        let mut encoder = JpegEncoder::new(&mut jpeg);
-        encoder.set_pixel_density(PixelDensity { density: (dpi, 72), unit: PixelDensityUnit::Inches });
-        encoder.encode_image(&image::RgbImage::from_pixel(60, 20, image::Rgb([20, 20, 20]))).unwrap();
-        let mut exif = b"Exif\0\0II\x2a\0\x08\0\0\0\x01\0\x12\x01\x03\0\x01\0\0\0".to_vec();
-        exif.extend_from_slice(&[orientation, 0, 0, 0, 0, 0, 0, 0]);
-        let mut out = jpeg[..2].to_vec();
-        out.extend_from_slice(&[0xff, 0xe1]);
-        out.extend_from_slice(&((exif.len() + 2) as u16).to_be_bytes());
-        out.extend_from_slice(&exif);
-        out.extend_from_slice(&jpeg[2..]);
-        out
-    }
+    use crate::tests::phone_jpeg;
 
     #[test]
     fn orientation_is_applied_and_plain_images_are_left_alone() {
@@ -111,23 +94,4 @@ mod tests {
         assert!(matches!(upright(b"\x89PNG\r\n\x1a\n"), Cow::Borrowed(_)));
         assert!(matches!(upright(b"\xff\xd8 not a jpeg"), Cow::Borrowed(_)));
     }
-
-    #[test]
-    fn a_phone_photo_used_as_a_custom_stamp_is_embedded_upright() {
-        let mut session = crate::Session::new();
-        let blank = session.create_blank(300.0, 400.0, 1).unwrap();
-        let id = session.open_new("form.pdf", blank).unwrap();
-        // A click places the stamp at its natural size: 30 x 20 pt as stored, 20 x 30 pt upright.
-        // Named "Signature" so `signature_image` finds its picture.
-        let file = MarkFile { name: "photo.jpg".into(), bytes: std::sync::Arc::new(phone_jpeg(6, 144)), page: 0 };
-        let stamp = Edit::AddCustomStamp { page: 0, rect: [100.0, 100.0, 100.0, 100.0], name: "Signature".into(), file, author: "Ada".into() };
-        session.apply(id, stamp).unwrap();
-        let cos = &session.get(id).unwrap().editor.as_ref().unwrap().cos;
-        let picture = pdfcraft_annot::signature_image(cos, 0, 0).unwrap().unwrap();
-        let obj = cos.get(picture);
-        let pdfcraft_cos::Object::Stream(s) = &*obj else { panic!() };
-        assert_eq!((s.dict.int(b"Width"), s.dict.int(b"Height")), (Some(20), Some(60)));
-        let rect = pdfcraft_annot::summaries(cos)[0].rect;
-        assert!(((rect[2] - rect[0]) - 20.0).abs() < 0.01 && ((rect[3] - rect[1]) - 30.0).abs() < 0.01, "{rect:?}");
-    }
 }

crates/engine/src/lib.rs

@@ -36,7 +36,6 @@ pub mod signature_image;
 pub mod signature_scan;
 pub mod text_fonts;
 mod text_preview;
-mod upright_image;
 pub mod word_count;
 pub mod xfa;
 
@@ -4933,7 +4932,7 @@ fn embed_image(
     name: &str,
     bytes: &[u8],
 ) -> Result<(pdfcraft_cos::ObjRef, (f64, f64)), pdfcraft_create::CreateError> {
-    pdfcraft_create::image_xobject(doc, name, &upright_image::upright(bytes))
+    pdfcraft_create::image_xobject(doc, name, bytes)
 }
 
 /// Bring a mark's picture into `doc`: a PDF page as a form XObject, or an image.

crates/engine/src/tests.rs

@@ -5854,3 +5854,39 @@ fn cropping_an_existing_image_clips_it_and_moves_with_it() {
     // No area, or a box off the image, is refused.
     assert!(s.apply(id, Edit::EditPageImage { page: 0, index: 0, change: ImageEdit::Crop([10.0, 10.0, 10.0, 50.0]) }).is_err());
 }
+
+/// A 60 x 20 JPEG at 144 x 72 dpi, tagged with EXIF Orientation 6 (shown turned 90 degrees clockwise).
+fn phone_jpeg() -> Vec<u8> {
+    use image::codecs::jpeg::{JpegEncoder, PixelDensity, PixelDensityUnit};
+    let mut jpeg = Vec::new();
+    let mut encoder = JpegEncoder::new(&mut jpeg);
+    encoder.set_pixel_density(PixelDensity { density: (144, 72), unit: PixelDensityUnit::Inches });
+    encoder.encode_image(&image::RgbImage::from_pixel(60, 20, image::Rgb([20, 20, 20]))).unwrap();
+    let mut exif = b"Exif\0\0II\x2a\0\x08\0\0\0\x01\0\x12\x01\x03\0\x01\0\0\0".to_vec();
+    exif.extend_from_slice(&[6, 0, 0, 0, 0, 0, 0, 0]);
+    let mut out = jpeg[..2].to_vec();
+    out.extend_from_slice(&[0xff, 0xe1]);
+    out.extend_from_slice(&((exif.len() + 2) as u16).to_be_bytes());
+    out.extend_from_slice(&exif);
+    out.extend_from_slice(&jpeg[2..]);
+    out
+}
+
+#[test]
+fn a_phone_photo_used_as_a_custom_stamp_is_embedded_upright() {
+    let mut session = Session::new();
+    let blank = session.create_blank(300.0, 400.0, 1).unwrap();
+    let id = session.open_new("form.pdf", blank).unwrap();
+    // A click places the stamp at its natural size: 30 x 20 pt as stored, 20 x 30 pt upright.
+    // Named "Signature" so `signature_image` finds its picture.
+    let file = MarkFile { name: "photo.jpg".into(), bytes: Arc::new(phone_jpeg()), page: 0 };
+    let stamp = Edit::AddCustomStamp { page: 0, rect: [100.0, 100.0, 100.0, 100.0], name: "Signature".into(), file, author: "Ada".into() };
+    session.apply(id, stamp).unwrap();
+    let cos = &session.get(id).unwrap().editor.as_ref().unwrap().cos;
+    let picture = pdfcraft_annot::signature_image(cos, 0, 0).unwrap().unwrap();
+    let obj = cos.get(picture);
+    let pdfcraft_cos::Object::Stream(s) = &*obj else { panic!() };
+    assert_eq!((s.dict.int(b"Width"), s.dict.int(b"Height")), (Some(20), Some(60)));
+    let rect = pdfcraft_annot::summaries(cos)[0].rect;
+    assert!(((rect[2] - rect[0]) - 20.0).abs() < 0.01 && ((rect[3] - rect[1]) - 30.0).abs() < 0.01, "{rect:?}");
+}