Skip to content

Accept XLUnicodeRichExtendedString without reserved tag #571

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jmcnamara merged 4 commits into from
Oct 24, 2025
Merged

Accept XLUnicodeRichExtendedString without reserved tag #571

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ede99a4
fix(xls): slightly more correct error message, (misleading when parsi…
sftse Oct 19, 2025
9fc6cf7
refactor(xls): remove distinction between None and vec.is_empty()
sftse Oct 19, 2025
c7ecac9
doc(xls): reference spec consistently
sftse Oct 19, 2025
32afc79
fix(xls): accept XLUnicodeRichExtendedString without reserved tag
sftse Oct 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 17 additions & 24 deletions src/xls.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@ impl std::fmt::Display for XlsError {
typ,
} => write!(
f,
"Invalid {typ} length, expected {expected} maximum, found {found}",
"Invalid {typ} length, expected at least {expected}, found {found}",
),
XlsError::ContinueRecordTooShort => write!(
f,
Expand Down Expand Up @@ -397,9 +397,7 @@ impl<RS: Read + Seek> Xls<RS> {
0x00EB => {
// MsoDrawingGroup
draw_group.extend(r.data);
if let Some(cont) = r.cont {
draw_group.extend(cont.iter().flat_map(|v| *v));
}
draw_group.extend(r.cont.iter().flat_map(|v| *v));
}
0x000A => break, // EOF,
_ => (),
Expand Down Expand Up @@ -933,10 +931,9 @@ fn parse_xf(r: &Record<'_>) -> Result<u16, XlsError> {
Ok(read_u16(&r.data[2..]))
}

/// Decode Format
/// Decode Format [MS-XLS 2.4.126]
///
/// See: <https://learn.microsoft.com/ru-ru/openspecs/office_file_formats/ms-xls/300280fd-e4fe-4675-a924-4d383af48d3b>
/// 2.4.126
fn parse_format(
r: &mut Record<'_>,
encoding: &XlsEncoding,
Expand All @@ -959,13 +956,17 @@ fn parse_format(
Ok((ifmt, detect_custom_number_format(&s)))
}

/// Decode `XLUnicodeRichExtendedString`.
/// Decode `XLUnicodeRichExtendedString` [MS-XLS 2.5.293].
///
/// See: <https://docs.microsoft.com/en-us/openspecs/office_file_formats/ms-xls/173d9f51-e5d3-43da-8de2-be7f22e119b9>
fn read_rich_extended_string(
r: &mut Record<'_>,
encoding: &XlsEncoding,
) -> Result<String, XlsError> {
if r.data.is_empty() {
// spec violation: at very least cch and flags should be present
return Ok(String::new());
}
if r.data.len() < 3 {
return Err(XlsError::Len {
typ: "rich extended string",
Expand Down Expand Up @@ -1041,21 +1042,16 @@ fn read_unicode_string_no_cch(encoding: &XlsEncoding, buf: &[u8], len: &usize, s
struct Record<'a> {
typ: u16,
data: &'a [u8],
cont: Option<Vec<&'a [u8]>>,
cont: Vec<&'a [u8]>,
}

impl<'a> Record<'a> {
fn continue_record(&mut self) -> bool {
match self.cont {
None => false,
Some(ref mut v) => {
if v.is_empty() {
false
} else {
self.data = v.remove(0);
true
}
}
if self.cont.is_empty() {
false
} else {
self.data = self.cont.remove(0);
true
}
}

Expand Down Expand Up @@ -1120,8 +1116,8 @@ impl<'a> Iterator for RecordIter<'a> {
let d = &data[4..];

// Append next record data if it is a Continue record
let cont = if next.len() > 4 && read_u16(next) == 0x003C {
let mut cont = Vec::new();
let mut cont = Vec::new();
if next.len() > 4 && read_u16(next) == 0x003C {
while self.stream.len() > 4 && read_u16(self.stream) == 0x003C {
len = read_u16(&self.stream[2..]) as usize;
if self.stream.len() < len + 4 {
Expand All @@ -1131,10 +1127,7 @@ impl<'a> Iterator for RecordIter<'a> {
cont.push(&sp.0[4..]);
self.stream = sp.1;
}
Some(cont)
} else {
None
};
}

Some(Ok(Record {
typ: t,
Expand Down