mirror of
https://github.com/storytold/wordcraft.git
synced 2026-11-10 04:09:53 -06:00
Merge remote-tracking branch 'upstream/main' into m3197
# Conflicts: # ROADMAP.md
This commit is contained in:
vangel76
+3
-1
File diff suppressed because one or more lines are too long
+19
-10
@@ -7,8 +7,9 @@
|
||||
/// makes it allocate gigabytes. Here the DIFAT is walked the way `cfb` walks it (header entries,
|
||||
/// then the DIFAT chain, at most one step per sector; trailing zero and free entries trimmed
|
||||
/// the same way) and the file is refused when it lists one FAT sector twice, or more FAT sectors
|
||||
/// than its sectors need (one FAT sector covers `sector_len / 4` of them, plus one spare), so the
|
||||
/// FAT `cfb` builds is about the size the file needs. Anything else that is wrong is left for
|
||||
/// than the file has sectors — every FAT sector is a sector of the file, so a longer list is
|
||||
/// duplicates or names `cfb` refuses anyway, and the FAT `cfb` builds (one sector of entries per
|
||||
/// listed name) stays within about the file's own size. Anything else that is wrong is left for
|
||||
/// `cfb` to report.
|
||||
pub fn check(bytes: &[u8]) -> Result<(), String> {
|
||||
const MAGIC: [u8; 8] = [0xD0, 0xCF, 0x11, 0xE0, 0xA1, 0xB1, 0x1A, 0xE1];
|
||||
@@ -52,12 +53,14 @@ pub fn check(bytes: &[u8]) -> Result<(), String> {
|
||||
while difat.last() == Some(&FREE) {
|
||||
difat.pop();
|
||||
}
|
||||
// Each listed FAT sector adds a whole sector of entries. A FAT sector holds the entries of
|
||||
// `sector_len / 4` sectors, so a file needs no more FAT sectors than that covers (one spare),
|
||||
// and none of them twice. A free entry in the middle is left for `cfb` to refuse.
|
||||
// Each listed FAT sector adds a whole sector of entries. A real file lists no more FAT
|
||||
// sectors than the file has — every FAT sector is a sector of the file, and none of them
|
||||
// twice (checked below) — so the FAT `cfb` builds stays within about the file's own size.
|
||||
// The #3642 blowup listed 2048 × 127 names in a ~1 MB file. A tighter bound (one FAT sector
|
||||
// per `sector_len / 4` sectors plus a spare) refused real files, whose writers reserve FAT
|
||||
// for growth: an encrypted package of 78 sectors lists 4 and didn't open (#5109).
|
||||
let listed: Vec<u32> = difat.into_iter().filter(|&s| s != FREE).collect();
|
||||
let needed = num_sectors.div_ceil(sector_len / 4).saturating_add(1);
|
||||
if listed.len() > needed {
|
||||
if listed.len() > num_sectors {
|
||||
return Err(format!("the DIFAT lists {} FAT sectors in a file of {num_sectors} sectors", listed.len()));
|
||||
}
|
||||
let mut seen = std::collections::HashSet::with_capacity(listed.len());
|
||||
@@ -123,10 +126,16 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_fat_sector_listed_twice_or_more_than_the_file_needs_is_refused() {
|
||||
// Each list is shorter than the file has sectors, which the guard used to accept.
|
||||
fn a_fat_sector_listed_twice_or_more_than_the_file_has_is_refused() {
|
||||
// A duplicate, and a list longer than the file has sectors: every FAT sector is a
|
||||
// sector of the file, so a longer list is one of the two.
|
||||
assert!(super::check(&header_difat(10, &[0, 0])).is_err_and(|e| e.contains("FAT sector 0 twice")));
|
||||
assert!(super::check(&header_difat(10, &[0, 1, 2])).is_err_and(|e| e.contains("3 FAT sectors")));
|
||||
assert!(
|
||||
super::check(&header_difat(10, &[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])).is_err_and(|e| e.contains("11 FAT sectors in a file of 10 sectors"))
|
||||
);
|
||||
// A writer may reserve FAT for growth: a real encrypted package of 78 sectors lists
|
||||
// 4 FAT sectors and didn't open since the #3642 guard landed (#5109).
|
||||
assert!(super::check(&header_difat(78, &[0, 1, 2, 3])).is_ok());
|
||||
assert!(super::check(&header_difat(10, &[0])).is_ok());
|
||||
assert!(super::check(&header_difat(200, &[0, 1])).is_ok());
|
||||
}
|
||||
|
||||
@@ -128,6 +128,9 @@ pub(super) struct Body<'a> {
|
||||
paras_done: usize,
|
||||
/// `(width, height, picture bytes, alt text, equation read from an embedded `draw:object`)`.
|
||||
frame: Option<Frame>,
|
||||
/// The first picture the open frame offers that WordCraft can't show: an object coming after it
|
||||
/// keeps it as its replacement.
|
||||
frame_unread: Option<Vec<u8>>,
|
||||
in_desc: bool,
|
||||
/// The master pages' page setups.
|
||||
pages: &'a Pages,
|
||||
@@ -259,6 +262,7 @@ impl<'a> Body<'a> {
|
||||
pending_master: None,
|
||||
paras_done: 0,
|
||||
frame: None,
|
||||
frame_unread: None,
|
||||
in_desc: false,
|
||||
pages,
|
||||
sec: page.clone(),
|
||||
@@ -1323,6 +1327,7 @@ impl Body<'_> {
|
||||
let w = get(a, "svg:width").and_then(length);
|
||||
let h = get(a, "svg:height").and_then(length);
|
||||
self.frame = Some((w, h, None, String::new(), None, None, None));
|
||||
self.frame_unread = None;
|
||||
let g = get(a, "draw:style-name").map(|s| self.styles.graphic(s)).unwrap_or_default();
|
||||
self.frame_float = Some(super::frames::place(a, w.unwrap_or(0.0), h.unwrap_or(0.0), &g, self.text_size()));
|
||||
self.member_start(a, w.unwrap_or(0.0), h.unwrap_or(0.0), None);
|
||||
@@ -1429,12 +1434,25 @@ impl Body<'_> {
|
||||
&& fr.2.is_none()
|
||||
&& fr.4.is_none()
|
||||
&& fr.5.is_none()
|
||||
&& fr.6.as_ref().is_none_or(|o| o.replacement.is_none())
|
||||
{
|
||||
let path = href.trim_start_matches("./");
|
||||
fr.2 = (self.zip)(path);
|
||||
if let Some(o) = &mut fr.6 {
|
||||
o.replacement = fr.2.clone().map(std::sync::Arc::new);
|
||||
// A frame may offer one picture in several formats, in order of preference
|
||||
// (LibreOffice writes its own `.svm` metafile before a PNG): the first
|
||||
// WordCraft can read. An object's replacement is the first, kept whatever it
|
||||
// is, also when the object is still to come.
|
||||
if let Some(d) = (self.zip)(path) {
|
||||
let readable = drawing::readable_picture(&d);
|
||||
match &mut fr.6 {
|
||||
Some(o) if o.replacement.is_none() => o.replacement = Some(std::sync::Arc::new(d.clone())),
|
||||
Some(_) => {}
|
||||
None if !readable => {
|
||||
self.frame_unread.get_or_insert_with(|| d.clone());
|
||||
}
|
||||
None => {}
|
||||
}
|
||||
if readable {
|
||||
fr.2 = Some(d);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1478,9 +1496,9 @@ impl Body<'_> {
|
||||
// A chart is kept whole too, to be written back as it was while it is unchanged.
|
||||
if fr.4.is_none() {
|
||||
fr.6 = super::objects::gather(href, ole, self.entries, self.manifest, &mut *self.zip);
|
||||
// A replacement picture read before the object.
|
||||
// A replacement picture read before the object: the first the frame offered.
|
||||
if let Some(o) = &mut fr.6 {
|
||||
o.replacement = fr.2.clone().map(std::sync::Arc::new);
|
||||
o.replacement = self.frame_unread.take().or_else(|| fr.2.clone()).map(std::sync::Arc::new);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -385,6 +385,11 @@ impl Body<'_> {
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether WordCraft can show these bytes as a picture (see the function below).
|
||||
pub(in crate::odt) fn readable_picture(data: &[u8]) -> bool {
|
||||
wordcraft_metafile::is_metafile(data) || model::sniff_image(data).is_some()
|
||||
}
|
||||
|
||||
/// A picture from a package's bytes: a raster image, or a Windows metafile (WMF, EMF: LibreOffice
|
||||
/// keeps clip art and logos so), sized `w` × `h` (points) when the frame says.
|
||||
pub(in crate::odt) fn picture(data: Vec<u8>, w: Option<f32>, h: Option<f32>, alt: &str) -> Option<model::Img> {
|
||||
|
||||
@@ -367,3 +367,33 @@ fn a_frame_keeps_its_place_in_the_stacking_order() {
|
||||
assert_eq!(float(&d).z, 0);
|
||||
assert!(crate::odt::tests::entry(&crate::odt::tests::export_model(&d).unwrap(), "content.xml").contains(r#"draw:z-index="0""#));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_frame_offering_several_formats_shows_the_first_it_can_read() {
|
||||
// LibreOffice's letter templates: its own metafile, then a PNG. Taking the first left nothing
|
||||
// to show, and the picture was gone once the paragraph was written from the model.
|
||||
let png = [b"\x89PNG\r\n\x1a\n".as_slice(), &[7u8; 64]].concat();
|
||||
let other = [b"\x89PNG\r\n\x1a\n".as_slice(), &[9u8; 64]].concat();
|
||||
let svm = b"VCLMTF a metafile WordCraft can't draw".to_vec();
|
||||
let frame = |images: &[&str]| {
|
||||
let images: String = images.iter().map(|h| format!(r#"<draw:image xlink:href="{h}"/>"#)).collect();
|
||||
format!(
|
||||
r#"<office:document-content {NS_T} {NS_D}><office:body><office:text><text:p><draw:frame svg:width="2in" svg:height="1in" text:anchor-type="as-char">{images}</draw:frame></text:p></office:text></office:body></office:document-content>"#
|
||||
)
|
||||
};
|
||||
let pictures = |d: &Document| d.body[0].as_para().unwrap().objects.iter().filter(|o| matches!(o, InlineObject::Image { .. })).count();
|
||||
let both = frame(&["Pictures/a.svm", "Pictures/a.png"]);
|
||||
let d = import(&zip_of(&[("content.xml", both.as_bytes()), ("Pictures/a.svm", &svm), ("Pictures/a.png", &png)])).unwrap();
|
||||
assert_eq!(pictures(&d), 1, "the PNG");
|
||||
let back = import(&crate::odt::tests::export_model(&d).unwrap()).unwrap();
|
||||
assert_eq!(pictures(&back), 1, "written from the model");
|
||||
// The first it can read, not the last.
|
||||
let order = frame(&["Pictures/a.png", "Pictures/b.png"]);
|
||||
let d = import(&zip_of(&[("content.xml", order.as_bytes()), ("Pictures/a.png", &png), ("Pictures/b.png", &other)])).unwrap();
|
||||
assert_eq!(pictures(&d), 1);
|
||||
assert_eq!(d.media.values().next().and_then(|m| m.get(8).copied()), Some(7), "the first");
|
||||
// Nothing it can read: no picture, and no failure.
|
||||
let only = frame(&["Pictures/a.svm"]);
|
||||
let d = import(&zip_of(&[("content.xml", only.as_bytes()), ("Pictures/a.svm", &svm)])).unwrap();
|
||||
assert_eq!(pictures(&d), 0);
|
||||
}
|
||||
|
||||
@@ -167,3 +167,84 @@ fn an_object_in_a_header_is_kept_too() {
|
||||
assert!(z.file_names().any(|n| n.ends_with("/content.xml") && n.starts_with("Object M")), "{:?}", z.file_names().collect::<Vec<_>>());
|
||||
assert!(entry(&saved, "styles.xml").contains("<draw:object xlink:href=\"./Object M"));
|
||||
}
|
||||
|
||||
/// A replacement picture may come before its object. It is kept whatever it is, though WordCraft
|
||||
/// can't show it, and a save from the model writes it back.
|
||||
#[test]
|
||||
fn a_replacement_picture_before_its_object_is_kept() {
|
||||
let content = format!(
|
||||
r#"<office:document-content {NS_T} {NS_D}><office:body><office:text><text:p>Sheet <draw:frame draw:name="Object1" text:anchor-type="as-char" svg:width="3in" svg:height="1in"><draw:image xlink:href="./ObjectReplacements/Object 1" xlink:type="simple"/><draw:object xlink:href="./Object 1" xlink:type="simple"/></draw:frame></text:p></office:text></office:body></office:document-content>"#
|
||||
);
|
||||
let bytes = zip_of(&[
|
||||
("META-INF/manifest.xml", MANIFEST.as_bytes()),
|
||||
("content.xml", content.as_bytes()),
|
||||
("Object 1/content.xml", SHEET.as_bytes()),
|
||||
("Object 1/styles.xml", b"<office:document-styles/>"),
|
||||
("ObjectReplacements/Object 1", METAFILE),
|
||||
]);
|
||||
let replacement = |bytes: &[u8]| {
|
||||
let flow = parse(bytes).unwrap();
|
||||
paras(&flow)
|
||||
.into_iter()
|
||||
.flat_map(|p| &p.inlines)
|
||||
.find_map(|i| if let Inline::Image(img) = i { img.object.clone() } else { None })
|
||||
.and_then(|o| o.replacement.clone())
|
||||
};
|
||||
assert_eq!(replacement(&bytes).as_deref().map(Vec::as_slice), Some(METAFILE));
|
||||
let saved = crate::odt::tests::export_model(&import(&bytes).unwrap()).unwrap();
|
||||
assert_eq!(replacement(&saved).as_deref().map(Vec::as_slice), Some(METAFILE), "written from the model");
|
||||
}
|
||||
|
||||
/// A readable picture after an unreadable replacement is what WordCraft shows, wherever the object
|
||||
/// comes between them, and a save from the model keeps both.
|
||||
#[test]
|
||||
fn a_readable_picture_after_an_unreadable_replacement_is_shown() {
|
||||
let mut png = std::io::Cursor::new(Vec::new());
|
||||
image::RgbImage::new(4, 4).write_to(&mut png, image::ImageFormat::Png).unwrap();
|
||||
let png = png.into_inner();
|
||||
let object = r#"<draw:object xlink:href="./Object 1"/>"#;
|
||||
let unread = r#"<draw:image xlink:href="./ObjectReplacements/Object 1"/>"#;
|
||||
let readable = r#"<draw:image xlink:href="./Pictures/a.png"/>"#;
|
||||
for frame in [format!("{unread}{object}{readable}"), format!("{object}{unread}{readable}")] {
|
||||
let content = format!(
|
||||
r#"<office:document-content {NS_T} {NS_D}><office:body><office:text><text:p>Sheet <draw:frame draw:name="Object1" text:anchor-type="as-char" svg:width="3in" svg:height="1in">{frame}</draw:frame></text:p></office:text></office:body></office:document-content>"#
|
||||
);
|
||||
let bytes = zip_of(&[
|
||||
("META-INF/manifest.xml", MANIFEST.as_bytes()),
|
||||
("content.xml", content.as_bytes()),
|
||||
("Object 1/content.xml", SHEET.as_bytes()),
|
||||
("Object 1/styles.xml", b"<office:document-styles/>"),
|
||||
("ObjectReplacements/Object 1", METAFILE),
|
||||
("Pictures/a.png", &png),
|
||||
]);
|
||||
let check = |bytes: &[u8], what: &str| {
|
||||
let flow = parse(bytes).unwrap();
|
||||
let img = paras(&flow)
|
||||
.into_iter()
|
||||
.flat_map(|p| &p.inlines)
|
||||
.find_map(|i| if let Inline::Image(img) = i { Some(img.clone()) } else { None })
|
||||
.unwrap();
|
||||
assert_eq!(img.data.as_slice(), png.as_slice(), "{what}: shows the picture it can read");
|
||||
assert_eq!(img.object.unwrap().replacement.as_deref().map(Vec::as_slice), Some(METAFILE), "{what}: keeps the replacement");
|
||||
};
|
||||
check(&bytes, "read");
|
||||
check(&crate::odt::tests::export_model(&import(&bytes).unwrap()).unwrap(), "written from the model");
|
||||
}
|
||||
}
|
||||
|
||||
/// With only an unreadable replacement, the placeholder drawn for it isn't written as a picture.
|
||||
#[test]
|
||||
fn the_placeholder_for_an_object_is_not_saved_as_its_picture() {
|
||||
let content = format!(
|
||||
r#"<office:document-content {NS_T} {NS_D}><office:body><office:text><text:p>Sheet <draw:frame draw:name="Object1" text:anchor-type="as-char" svg:width="3in" svg:height="1in"><draw:object xlink:href="./Object 1"/><draw:image xlink:href="./ObjectReplacements/Object 1"/></draw:frame></text:p></office:text></office:body></office:document-content>"#
|
||||
);
|
||||
let bytes = zip_of(&[
|
||||
("META-INF/manifest.xml", MANIFEST.as_bytes()),
|
||||
("content.xml", content.as_bytes()),
|
||||
("Object 1/content.xml", SHEET.as_bytes()),
|
||||
("Object 1/styles.xml", b"<office:document-styles/>"),
|
||||
("ObjectReplacements/Object 1", METAFILE),
|
||||
]);
|
||||
let saved = crate::odt::tests::export_model(&import(&bytes).unwrap()).unwrap();
|
||||
assert_eq!(entry(&saved, "content.xml").matches("<draw:image ").count(), 1);
|
||||
}
|
||||
|
||||
@@ -244,11 +244,19 @@ impl Writer {
|
||||
None => self.pictures.push((replacement.clone(), img.data.clone(), mime_of(&img.ext).to_string())),
|
||||
}
|
||||
let el = if o.ole { "draw:object-ole" } else { "draw:object" };
|
||||
format!(
|
||||
let mut inner = format!(
|
||||
"<{el} xlink:href=\"./{}\" xlink:type=\"simple\" xlink:show=\"embed\" xlink:actuate=\"onLoad\"/><draw:image xlink:href=\"./{}\" xlink:type=\"simple\" xlink:show=\"embed\" xlink:actuate=\"onLoad\"/>",
|
||||
x(&name),
|
||||
x(&replacement)
|
||||
)
|
||||
);
|
||||
// A picture shown that isn't the replacement (one WordCraft can't read) follows it; a
|
||||
// placeholder is WordCraft's own, not the file's.
|
||||
let other = o.replacement.as_ref().is_some_and(|r| r.as_slice() != img.data.as_slice());
|
||||
if other && crate::odt::objects::placeholder(&o.mime).as_deref() != Some(img.data.as_slice()) {
|
||||
let href = self.picture(img);
|
||||
inner.push_str(&format!("<draw:image xlink:href=\"{href}\" xlink:type=\"simple\" xlink:show=\"embed\" xlink:actuate=\"onLoad\"/>"));
|
||||
}
|
||||
inner
|
||||
}
|
||||
|
||||
/// Object `o` (a chart as read) in the package under the next object name, with its
|
||||
|
||||
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user