mirror of
https://github.com/storytold/wordcraft.git
synced 2026-10-25 19:07:17 -06:00
rabis7575andClaude Opus 5.5
663de991df
The Word XML Document (Flat OPC) reader counted only the parts it kept: a repeated or nameless part, a child of the package that isn't a part and anything nested inside one were read without being counted, nesting had no cap, and a part's inline XML was copied before its size was checked. Every child of the package now counts against the part limit and every part's data against the part and package size limits, kept or not; nesting and the elements of each child are capped as the XML tree reader caps a part's; and data is checked before it is copied. Base64 in pkg:binaryData was taken from plain text only, so CDATA and character references were dropped and a picture written that way lost bytes. Both now read as the same text, and an entity there is an invalid base64 error. Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
263 lines
17 KiB
Rust
263 lines
17 KiB
Rust
//! Word XML files (#548): Flat OPC (Word XML Document) and Word 2003 XML, from hand-written
|
|
//! samples (never files produced by Word).
|
|
|
|
use base64::Engine as _;
|
|
use wordcraft_doc::props::Align;
|
|
use wordcraft_doc::section::NumFormat;
|
|
use wordcraft_doc::{Block, Document, InlineObject, Paragraph};
|
|
use wordcraft_docx::{DocxError, XmlKind, read_xml, sniff_xml};
|
|
|
|
fn paras(doc: &Document) -> Vec<&Paragraph> {
|
|
doc.body.iter().filter_map(|b| b.as_para()).collect()
|
|
}
|
|
|
|
fn part_text(doc: &Document, id: Option<u32>) -> String {
|
|
id.and_then(|i| doc.parts.get(&i))
|
|
.map(|p| p.blocks.iter().filter_map(|b| b.as_para()).map(|p| p.plain_text()).collect::<Vec<_>>().join("\n"))
|
|
.unwrap_or_default()
|
|
}
|
|
|
|
fn tiny_png_b64() -> String {
|
|
let img = image::RgbaImage::from_fn(2, 2, |x, y| image::Rgba([x as u8 * 100, y as u8 * 100, 50, 255]));
|
|
let mut out = std::io::Cursor::new(Vec::new());
|
|
img.write_to(&mut out, image::ImageFormat::Png).unwrap();
|
|
let b64 = base64::engine::general_purpose::STANDARD.encode(out.into_inner());
|
|
// Line breaks inside base64, as the formats write it.
|
|
b64.as_bytes().chunks(20).map(|c| std::str::from_utf8(c).unwrap()).collect::<Vec<_>>().join("\n")
|
|
}
|
|
|
|
/// A minimal Flat OPC package written by hand: namespaces declared on the package element only,
|
|
/// a hyperlink relationship, a picture in base64 and an empty part.
|
|
#[test]
|
|
fn reads_a_hand_written_flat_opc_package() {
|
|
let png = tiny_png_b64();
|
|
let xml = format!(
|
|
r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
|
<?mso-application progid="Word.Document"?>
|
|
<pkg:package xmlns:pkg="http://schemas.microsoft.com/office/2006/xmlPackage" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
|
|
<pkg:part pkg:name="/_rels/.rels" pkg:contentType="application/vnd.openxmlformats-package.relationships+xml">
|
|
<pkg:xmlData>
|
|
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>
|
|
</pkg:xmlData>
|
|
</pkg:part>
|
|
<pkg:part pkg:name="/word/_rels/document.xml.rels" pkg:contentType="application/vnd.openxmlformats-package.relationships+xml">
|
|
<pkg:xmlData><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId5" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/hyperlink" Target="https://example.org/flat" TargetMode="External"/><Relationship Id="rId6" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/image" Target="media/dot.png"/></Relationships></pkg:xmlData>
|
|
</pkg:part>
|
|
<pkg:part pkg:name="/word/document.xml" pkg:contentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml">
|
|
<pkg:xmlData>
|
|
<w:document xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:v="urn:schemas-microsoft-com:vml"><w:body>
|
|
<w:p><w:r><w:rPr><w:b/></w:rPr><w:t>Seed & soil</w:t></w:r></w:p>
|
|
<w:p><w:hyperlink r:id="rId5"><w:r><w:t>link</w:t></w:r></w:hyperlink></w:p>
|
|
<w:p><w:r><w:pict><v:shape style="width:24pt;height:12pt"><v:imagedata r:id="rId6"/></v:shape></w:pict></w:r></w:p>
|
|
</w:body></w:document>
|
|
</pkg:xmlData>
|
|
</pkg:part>
|
|
<pkg:part pkg:name="/word/media/dot.png" pkg:contentType="image/png" pkg:compression="store">
|
|
<pkg:binaryData>{png}</pkg:binaryData>
|
|
</pkg:part>
|
|
<pkg:part pkg:name="/word/empty.xml" pkg:contentType="application/xml"><pkg:xmlData/></pkg:part>
|
|
</pkg:package>"#
|
|
);
|
|
assert_eq!(sniff_xml(xml.as_bytes()), XmlKind::FlatOpc);
|
|
let doc = read_xml(xml.as_bytes()).unwrap();
|
|
let ps = paras(&doc);
|
|
assert_eq!(ps[0].plain_text(), "Seed & soil");
|
|
assert_eq!(ps[0].props_at(0).bold, Some(true));
|
|
assert_eq!(ps[1].props_at(0).link.as_deref(), Some("https://example.org/flat"));
|
|
assert!(matches!(ps[2].objects.first(), Some(InlineObject::Image { w, h, .. }) if *w == 24.0 && *h == 12.0));
|
|
assert_eq!(doc.media.len(), 1);
|
|
}
|
|
|
|
/// A Word 2003 XML Document, hand-written from the Office 2003 XML Reference Schemas.
|
|
fn wordml_2003_sample() -> String {
|
|
let png = tiny_png_b64();
|
|
format!(
|
|
r##"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
|
<?mso-application progid="Word.Document"?>
|
|
<w:wordDocument xmlns:w="http://schemas.microsoft.com/office/word/2003/wordml" xmlns:wx="http://schemas.microsoft.com/office/word/2003/auxHint" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:aml="http://schemas.microsoft.com/aml/2001/core" w:macrosPresent="no">
|
|
<o:DocumentProperties><o:Title>Garden notes</o:Title><o:Author>Ada Gardener</o:Author><o:Keywords>beans</o:Keywords></o:DocumentProperties>
|
|
<w:fonts><w:defaultFonts w:ascii="Georgia" w:fareast="Georgia" w:h-ansi="Georgia" w:cs="Georgia"/></w:fonts>
|
|
<w:lists>
|
|
<w:listDef w:listDefId="3"><w:plt w:val="HybridMultilevel"/>
|
|
<w:lvl w:ilvl="0"><w:start w:val="1"/><w:nfc w:val="4"/><w:lvlText w:val="%1)"/><w:lvlJc w:val="left"/><w:pPr><w:ind w:left="720" w:hanging="360"/></w:pPr></w:lvl>
|
|
</w:listDef>
|
|
<w:list w:ilfo="2"><w:ilst w:val="3"/></w:list>
|
|
</w:lists>
|
|
<w:styles>
|
|
<w:versionOfBuiltInStyleNames w:val="4"/>
|
|
<w:style w:type="paragraph" w:default="on" w:styleId="Normal"><w:name w:val="Normal"/><w:rPr><wx:font wx:val="Georgia"/><w:sz w:val="24"/><w:sz-cs w:val="24"/></w:rPr></w:style>
|
|
<w:style w:type="paragraph" w:styleId="Heading1"><w:name w:val="heading 1"/><wx:uiName wx:val="Heading 1"/><w:basedOn w:val="Normal"/><w:next w:val="Normal"/><w:pPr><w:keepNext/><w:spacing w:before="240" w:after="60"/><w:outlineLvl w:val="0"/></w:pPr><w:rPr><w:b/><w:sz w:val="32"/></w:rPr></w:style>
|
|
</w:styles>
|
|
<w:docPr><w:view w:val="print"/><w:zoom w:percent="100"/><w:footnotePr><w:footnote w:type="separator"><w:p><w:r><w:separator/></w:r></w:p></w:footnote></w:footnotePr></w:docPr>
|
|
<w:body>
|
|
<wx:sect>
|
|
<w:p><w:pPr><w:pStyle w:val="Heading1"/></w:pPr><aml:annotation aml:id="0" w:type="Word.Bookmark.Start" w:name="plan"/><aml:annotation aml:id="1" w:type="Word.Comment.Start"/><w:r><w:t>Plan</w:t></w:r><aml:annotation aml:id="1" w:type="Word.Comment.End"/><w:r><aml:annotation aml:id="1" aml:author="Bo" w:initials="B" w:type="Word.Comment"><aml:content><w:p><w:r><w:t>Too short?</w:t></w:r></w:p></aml:content></aml:annotation></w:r><aml:annotation aml:id="0" w:type="Word.Bookmark.End"/></w:p>
|
|
<w:p><w:pPr><w:jc w:val="center"/><w:ind w:first-line="360"/><w:spacing w:line="360" w:line-rule="auto"/></w:pPr>
|
|
<w:r><w:t>Plain </w:t></w:r>
|
|
<w:r><w:rPr><w:rFonts w:ascii="Courier New" w:h-ansi="Courier New"/><w:b/><w:i/><w:u w:val="single"/><w:sz w:val="28"/><w:color w:val="FF0000"/></w:rPr><w:t>loud</w:t></w:r>
|
|
<w:r><w:tab/><w:t>then</w:t><w:br/><w:t>more</w:t></w:r>
|
|
<w:r><w:footnote><w:p><w:r><w:footnoteRef/></w:r><w:r><w:t>Sown in May.</w:t></w:r></w:p></w:footnote></w:r>
|
|
</w:p>
|
|
<w:p><w:hlink w:dest="https://example.org/beans" w:screenTip="Beans"><w:r><w:rPr><w:rStyle w:val="Hyperlink"/></w:rPr><w:t>bean guide</w:t></w:r></w:hlink></w:p>
|
|
<w:p><w:pPr><w:listPr><w:ilvl w:val="0"/><w:ilfo w:val="2"/><wx:t wx:val="a)"/></w:listPr></w:pPr><w:r><w:t>Water the beans</w:t></w:r><aml:annotation aml:id="7" aml:author="Ada" aml:createdate="2004-05-01T10:00:00Z" w:type="Word.Insertion"><aml:content><w:r><w:t> daily</w:t></w:r></aml:content></aml:annotation></w:p>
|
|
<w:tbl>
|
|
<w:tblPr><w:tblW w:w="0" w:type="auto"/></w:tblPr>
|
|
<w:tblGrid><w:gridCol w:w="2000"/><w:gridCol w:w="2000"/></w:tblGrid>
|
|
<w:tr><w:tc><w:tcPr><w:tcW w:w="2000" w:type="dxa"/><w:vmerge w:val="restart"/></w:tcPr><w:p><w:r><w:t>A1</w:t></w:r></w:p></w:tc><w:tc><w:tcPr><w:tcW w:w="2000" w:type="dxa"/></w:tcPr><w:p><w:r><w:t>B1</w:t></w:r></w:p></w:tc></w:tr>
|
|
<w:tr><w:tc><w:tcPr><w:tcW w:w="2000" w:type="dxa"/><w:vmerge/></w:tcPr><w:p/></w:tc><w:tc><w:tcPr><w:tcW w:w="2000" w:type="dxa"/></w:tcPr><w:p><w:r><w:t>B2</w:t></w:r></w:p></w:tc></w:tr>
|
|
</w:tbl>
|
|
<w:p><w:r><w:pict><w:binData w:name="wordml://02000001.png">{png}</w:binData><v:shape id="_x0000_i1025" type="#_x0000_t75" style="width:36pt;height:18pt"><v:imagedata src="wordml://02000001.png" o:title="dot"/></v:shape></w:pict></w:r></w:p>
|
|
<w:sectPr>
|
|
<w:hdr w:type="odd"><w:p><w:r><w:t>Garden header</w:t></w:r></w:p></w:hdr>
|
|
<w:pgSz w:w="12240" w:h="15840"/><w:pgMar w:top="1440" w:right="1800" w:bottom="1440" w:left="1800" w:header="720" w:footer="720" w:gutter="0"/>
|
|
</w:sectPr>
|
|
</wx:sect>
|
|
</w:body>
|
|
</w:wordDocument>"##
|
|
)
|
|
}
|
|
|
|
#[test]
|
|
fn imports_word_2003_xml() {
|
|
let xml = wordml_2003_sample();
|
|
assert_eq!(sniff_xml(xml.as_bytes()), XmlKind::WordMl2003);
|
|
let doc = read_xml(xml.as_bytes()).unwrap();
|
|
assert_eq!(doc.core.title, "Garden notes");
|
|
assert_eq!(doc.core.creator, "Ada Gardener");
|
|
|
|
let h1 = doc.styles.get("Heading1").expect("Heading1 style");
|
|
assert_eq!(h1.chr.bold, Some(true));
|
|
assert_eq!(h1.chr.size, Some(16.0));
|
|
|
|
let ps = paras(&doc);
|
|
assert_eq!(ps[0].plain_text(), "Plan");
|
|
assert_eq!(ps[0].props.style.as_deref(), Some("Heading1"));
|
|
assert!(ps[0].objects.iter().any(|o| matches!(o, InlineObject::BookmarkStart { name, .. } if name == "plan")));
|
|
|
|
let p = ps[1];
|
|
assert_eq!(p.props.align, Some(Align::Center));
|
|
assert_eq!(p.props.indent_first, Some(18.0));
|
|
let loud = p.text.find("loud").unwrap();
|
|
let c = p.props_of_char(loud);
|
|
assert_eq!((c.bold, c.italic, c.size, c.font.as_deref()), (Some(true), Some(true), Some(14.0), Some("Courier New")));
|
|
assert!(c.underline.is_some() && c.color.is_some());
|
|
assert!(p.plain_text().contains("Plain loud\tthen"));
|
|
let note = p.objects.iter().find_map(|o| match o {
|
|
InlineObject::NoteRef { id, .. } => Some(*id),
|
|
_ => None,
|
|
});
|
|
assert_eq!(part_text(&doc, note), "Sown in May.");
|
|
|
|
assert_eq!(ps[2].props_at(0).link.as_deref(), Some("https://example.org/beans"));
|
|
let listed = ps[3];
|
|
let num = listed.props.numbering.expect("list paragraph");
|
|
let lvl = doc.numbering.level(num.num, num.level).expect("list level");
|
|
assert_eq!((lvl.format, lvl.text.as_str(), lvl.indent), (NumFormat::LowerLetter, "%1)", 36.0));
|
|
let ins = listed.props_of_char(listed.text.find("daily").unwrap()).ins.and_then(|i| doc.revisions.get(i as usize));
|
|
assert_eq!(ins.map(|r| r.author.as_str()), Some("Ada"));
|
|
let comment = doc.comments.values().next().expect("comment");
|
|
assert_eq!((comment.author.as_str(), part_text(&doc, Some(comment.part)).as_str()), ("Bo", "Too short?"));
|
|
|
|
let table = doc.body.iter().find_map(|b| match b.as_ref() {
|
|
Block::Table(t) => Some(t),
|
|
_ => None,
|
|
});
|
|
let table = table.expect("table");
|
|
assert_eq!(table.rows.len(), 2);
|
|
assert_eq!(table.rows[0].cells[1].blocks.first().and_then(|b| b.as_para()).map(|p| p.plain_text()).as_deref(), Some("B1"));
|
|
|
|
let pic = ps.iter().flat_map(|p| p.objects.iter()).find(|o| matches!(o, InlineObject::Image { .. }));
|
|
assert!(matches!(pic, Some(InlineObject::Image { w, h, .. }) if *w == 36.0 && *h == 18.0));
|
|
assert_eq!(doc.media.len(), 1);
|
|
|
|
assert_eq!(doc.last_section.page_w, 612.0);
|
|
assert_eq!(doc.last_section.margin_left, 90.0);
|
|
assert_eq!(part_text(&doc, doc.last_section.headers.default), "Garden header");
|
|
}
|
|
|
|
#[test]
|
|
fn hostile_word_xml_is_an_error_not_a_panic() {
|
|
let flat = r#"<pkg:package xmlns:pkg="http://schemas.microsoft.com/office/2006/xmlPackage">"#;
|
|
let w2003 = r#"<w:wordDocument xmlns:w="http://schemas.microsoft.com/office/word/2003/wordml">"#;
|
|
// Other XML (and non-XML) is refused with the Word XML error.
|
|
for other in ["<html><body>hi</body></html>", "", "not xml at all", "<package/>"] {
|
|
assert_eq!(read_xml(other.as_bytes()), Err(DocxError::NotWordXml), "{other:?}");
|
|
}
|
|
// Broken packages: errors.
|
|
for bad in [
|
|
flat.to_string(),
|
|
format!("{flat}</pkg:package>"),
|
|
format!("{flat}<pkg:part pkg:name=\"/word/document.xml\"><pkg:binaryData>!!!not base64</pkg:binaryData></pkg:part></pkg:package>"),
|
|
format!("{flat}<pkg:part pkg:name=\"/word/document.xml\"><pkg:xmlData><w:document></pkg:xmlData></pkg:part></pkg:package>"),
|
|
] {
|
|
assert!(read_xml(bad.as_bytes()).is_err(), "{bad}");
|
|
}
|
|
// Lenient leftovers never panic.
|
|
for odd in [
|
|
format!("{flat}<pkg:part/><pkg:part pkg:name=\"\"><pkg:xmlData/></pkg:part><x/></pkg:package>"),
|
|
format!(
|
|
"{w2003}<w:body><w:p><w:r><w:footnote w:type=\"separator\"/><w:pict><w:binData w:name=\"a\">%%%</w:binData><v:imagedata src=\"a\"/></w:pict></w:r></w:p></w:body></w:wordDocument>"
|
|
),
|
|
format!(
|
|
"{w2003}<w:lists><w:list/><w:listDef/></w:lists><w:body><aml:annotation xmlns:aml=\"http://schemas.microsoft.com/aml/2001/core\" aml:id=\"x\" w:type=\"Word.Comment\"/><w:sectPr><w:hdr/><w:ftr w:type=\"first\"/></w:sectPr></w:body></w:wordDocument>"
|
|
),
|
|
format!("{w2003}{}", "<w:p>".repeat(5000)),
|
|
] {
|
|
let _ = read_xml(odd.as_bytes());
|
|
}
|
|
// Too many parts.
|
|
let mut many = String::from(flat);
|
|
for i in 0..20_001 {
|
|
many.push_str(&format!("<pkg:part pkg:name=\"/p{i}.bin\"><pkg:binaryData>AA==</pkg:binaryData></pkg:part>"));
|
|
}
|
|
many.push_str("</pkg:package>");
|
|
assert!(matches!(read_xml(many.as_bytes()), Err(DocxError::Limit(_))));
|
|
}
|
|
|
|
/// A Flat OPC package of one paragraph with a picture, whose `pkg:binaryData` holds `data` as
|
|
/// written, and `extra` after the parts.
|
|
fn picture_package(data: &str, extra: &str) -> String {
|
|
format!(
|
|
r#"<pkg:package xmlns:pkg="http://schemas.microsoft.com/office/2006/xmlPackage" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
|
|
<pkg:part pkg:name="/_rels/.rels" pkg:contentType="application/vnd.openxmlformats-package.relationships+xml"><pkg:xmlData><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships></pkg:xmlData></pkg:part>
|
|
<pkg:part pkg:name="/word/_rels/document.xml.rels" pkg:contentType="application/vnd.openxmlformats-package.relationships+xml"><pkg:xmlData><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId6" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/image" Target="media/dot.png"/></Relationships></pkg:xmlData></pkg:part>
|
|
<pkg:part pkg:name="/word/document.xml" pkg:contentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"><pkg:xmlData><w:document xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:v="urn:schemas-microsoft-com:vml"><w:body><w:p><w:r><w:t>Seed</w:t></w:r><w:r><w:pict><v:shape style="width:24pt;height:12pt"><v:imagedata r:id="rId6"/></v:shape></w:pict></w:r></w:p></w:body></w:document></pkg:xmlData></pkg:part>
|
|
<pkg:part pkg:name="/word/media/dot.png" pkg:contentType="image/png" pkg:compression="store"><pkg:binaryData>{data}</pkg:binaryData></pkg:part>{extra}
|
|
</pkg:package>"#
|
|
)
|
|
}
|
|
|
|
/// A binary part's base64 reads the same as plain text, as CDATA or with character references;
|
|
/// an entity in it is an error rather than bytes gone missing (#1353).
|
|
#[test]
|
|
fn flat_opc_binary_data_reads_the_same_in_cdata_and_character_references() {
|
|
let png = tiny_png_b64();
|
|
let media = |data: &str| read_xml(picture_package(data, "").as_bytes()).map(|d| d.media.values().cloned().collect::<Vec<_>>());
|
|
let plain = media(&png).unwrap();
|
|
assert_eq!(plain.len(), 1);
|
|
let (head, tail) = png.split_at(png.len() / 2);
|
|
let first = png.chars().next().unwrap();
|
|
for other in
|
|
[format!("<![CDATA[{png}]]>"), format!("{head}<![CDATA[{tail}]]>"), format!("&#{};{}", u32::from(first), &png[1..]).replace('\n', "
")]
|
|
{
|
|
assert_eq!(media(&other).unwrap(), plain, "{other}");
|
|
}
|
|
assert!(media(&format!("&{png}")).is_err());
|
|
}
|
|
|
|
/// Work anywhere in a Flat OPC file is bounded, not only in the parts that are kept: nesting
|
|
/// and elements no part reader looks at, and repeated part names, count too (#1353).
|
|
#[test]
|
|
fn flat_opc_limits_count_what_is_not_kept() {
|
|
let png = tiny_png_b64();
|
|
let limited = |extra: &str| matches!(read_xml(picture_package(&png, extra).as_bytes()), Err(DocxError::Limit(_)));
|
|
assert!(read_xml(picture_package(&png, "<x/>").as_bytes()).is_ok());
|
|
// Deep nesting outside the parts.
|
|
assert!(limited(&format!("<x>{}{}</x>", "<y>".repeat(1000), "</y>".repeat(1000))));
|
|
// One part name over and over, or other elements, past the part count.
|
|
assert!(limited(&r#"<pkg:part pkg:name="/word/media/dot.png"><pkg:binaryData>AA==</pkg:binaryData></pkg:part>"#.repeat(20_000)));
|
|
assert!(limited(&"<x/>".repeat(20_000)));
|
|
// A part nothing reads, one element over what the XML tree reader takes in a part (8 000 000).
|
|
assert!(limited(&format!(r#"<pkg:part pkg:name="/word/unused.xml"><pkg:xmlData><r>{}</r></pkg:xmlData></pkg:part>"#, "<y/>".repeat(8_000_000))));
|
|
}
|