aleleba/wordcraft
1
0
Fork 0
mirror of https://github.com/storytold/wordcraft.git synced 2026-10-30 21:37:41 -06:00
Code Issues Packages Projects Releases Wiki Activity

fix(formats): support xs:time, string-value, and case-insensitive cell types in spreadsheets

Browse Source
This commit is contained in:
Divyanshu Gupta
2026-10-16 04:39:59 +05:30
parent 86adfd34eb
commit 772cccf038
1 changed files with 83 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/formats/src/sheet.rs
+83 -29
View File
@@ -666,19 +666,24 @@ fn xlsx_rows(pkg: &mut Package<'_>, path: &str) -> Result<Vec<Vec<String>>, Stri
fn xlsx_value(c: &XCell, shared: &[String], formats: &[Option<DateKind>], date1904: bool) -> String {
let v = c.value.trim();
match c.kind.as_str() {
"s" => v.parse::<usize>().ok().and_then(|i| shared.get(i)).cloned().unwrap_or_default(),
"inlineStr" => c.inline.clone(),
"str" | "e" => c.value.clone(),
"b" => if v == "1" || v.eq_ignore_ascii_case("true") { "TRUE" } else { "FALSE" }.into(),
"d" => iso_datetime(v).unwrap_or_else(|| v.to_string()),
_ if v.is_empty() => c.inline.clone(),
_ => {
let Ok(x) = v.parse::<f64>() else { return v.to_string() };
match formats.get(c.style).copied().flatten() {
Some(kind) => serial_date(x, date1904, kind).unwrap_or_else(|| number(x)),
None => number(x),
}
let kind = c.kind.trim();
if kind.eq_ignore_ascii_case("s") {
v.parse::<usize>().ok().and_then(|i| shared.get(i)).cloned().unwrap_or_default()
} else if kind.eq_ignore_ascii_case("inlineStr") {
if c.inline.is_empty() { c.value.clone() } else { c.inline.clone() }
} else if kind.eq_ignore_ascii_case("str") || kind.eq_ignore_ascii_case("e") {
c.value.clone()
} else if kind.eq_ignore_ascii_case("b") {
if v == "1" || v.eq_ignore_ascii_case("true") { "TRUE" } else { "FALSE" }.into()
} else if kind.eq_ignore_ascii_case("d") {
iso_datetime(v).unwrap_or_else(|| v.to_string())
} else if v.is_empty() {
c.inline.clone()
} else {
let Ok(x) = v.parse::<f64>() else { return v.to_string() };
match formats.get(c.style).copied().flatten() {
Some(kind) => serial_date(x, date1904, kind).unwrap_or_else(|| number(x)),
None => number(x),
}
}
}
@@ -763,22 +768,31 @@ fn iso_datetime(v: &str) -> Option<String> {
Some(out)
}
/// An ISO 8601 duration time (`PT13H45M00S`) as `hh:mm[:ss]`.
/// An ISO 8601 duration time (`PT13H45M00S`) or clock time (`13:45[:00]`) as `hh:mm[:ss]`.
fn iso_time(v: &str) -> Option<String> {
let t = v.trim().strip_prefix("PT")?;
let (mut h, mut m, mut s) = (0u64, 0u64, 0f64);
let mut num = String::new();
for c in t.chars() {
match c {
'H' => h = std::mem::take(&mut num).parse().ok()?,
'M' => m = std::mem::take(&mut num).parse().ok()?,
'S' => s = std::mem::take(&mut num).parse().ok()?,
c if num.len() < 20 => num.push(c),
_ => return None,
let t = v.trim();
if let Some(t) = t.strip_prefix("PT") {
let (mut h, mut m, mut s) = (0u64, 0u64, 0f64);
let mut num = String::new();
for c in t.chars() {
match c {
'H' => h = std::mem::take(&mut num).parse().ok()?,
'M' => m = std::mem::take(&mut num).parse().ok()?,
'S' => s = std::mem::take(&mut num).parse().ok()?,
c if num.len() < 20 => num.push(c),
_ => return None,
}
}
let s = s.round() as u64;
return Some(if s == 0 { format!("{h:02}:{m:02}") } else { format!("{h:02}:{m:02}:{s:02}") });
}
let s = s.round() as u64;
Some(if s == 0 { format!("{h:02}:{m:02}") } else { format!("{h:02}:{m:02}:{s:02}") })
// xs:time: hh:mm[:ss[.sss]][Z|+...]
let hms: Vec<u32> = t.split(['Z', '+', '-']).next().unwrap_or("").split(':').filter_map(|p| p.split('.').next().and_then(|x| x.parse().ok())).collect();
if let [h, mi, rest @ ..] = hms.as_slice() {
let s = rest.first().copied().unwrap_or(0);
return Some(if s == 0 { format!("{h:02}:{mi:02}") } else { format!("{h:02}:{mi:02}:{s:02}") });
}
None
}
// ---------------------------------------------------------------------------------------------
@@ -827,11 +841,13 @@ fn ods_read(xml: &[u8], want: Option<usize>) -> Result<(Vec<String>, Vec<Vec<Str
b"table-cell" | b"covered-table-cell" if row.is_some() => {
let repeat = attr(e, b"number-columns-repeated").and_then(|v| v.trim().parse().ok()).unwrap_or(1u64).max(1);
let kind = attr(e, b"value-type").unwrap_or_default();
let value = match kind.as_str() {
"float" => attr(e, b"value"),
let kind_lower = kind.trim().to_ascii_lowercase();
let value = match kind_lower.as_str() {
"float" | "percentage" | "currency" => attr(e, b"value"),
"date" => attr(e, b"date-value"),
"time" => attr(e, b"time-value"),
"boolean" => attr(e, b"boolean-value"),
"string" => attr(e, b"string-value"),
_ => None,
};
// A covered cell's own content is hidden by the merge.
@@ -935,11 +951,16 @@ fn ods_read(xml: &[u8], want: Option<usize>) -> Result<(Vec<String>, Vec<Vec<Str
fn ods_value(c: &OCell) -> String {
let v = c.value.as_deref().map(str::trim);
match (c.kind.as_str(), v) {
let kind = c.kind.trim().to_ascii_lowercase();
match (kind.as_str(), v) {
("float", Some(v)) => v.parse::<f64>().map(number).unwrap_or_else(|_| c.text.clone()),
("date", Some(v)) => iso_datetime(v).unwrap_or_else(|| c.text.clone()),
("time", Some(v)) => iso_time(v).unwrap_or_else(|| c.text.clone()),
("boolean", Some(v)) => if v.eq_ignore_ascii_case("true") || v == "1" { "TRUE" } else { "FALSE" }.into(),
("percentage" | "currency", Some(v)) if c.text.trim().is_empty() => {
v.parse::<f64>().map(number).unwrap_or_else(|_| c.text.clone())
}
("string", Some(v)) if c.text.trim().is_empty() => v.to_string(),
_ => c.text.clone(),
}
}
@@ -1066,4 +1087,37 @@ mod tests {
assert_eq!(number(1234567.0), "1234567");
assert_eq!(number(0.1 + 0.2), "0.3");
}
#[test]
fn test_sheet_extended_value_parsing() {
assert_eq!(iso_time("13:45:00").as_deref(), Some("13:45"));
assert_eq!(iso_time("13:45:30.500").as_deref(), Some("13:45:30"));
assert_eq!(iso_time("13:45:30Z").as_deref(), Some("13:45:30"));
assert_eq!(iso_time("PT13H45M").as_deref(), Some("13:45"));
// ODS with string-value and percentage without text:p, and case-insensitive float
let content = r#"<office:document-content xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:table="urn:oasis:names:tc:opendocument:xmlns:table:1.0" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0">
<office:body><office:spreadsheet><table:table table:name="Sheet1">
<table:table-row>
<table:table-cell office:value-type="STRING" office:string-value="Hello"/>
<table:table-cell office:value-type="percentage" office:value="0.15"/>
<table:table-cell office:value-type="FLOAT" office:value="42"/>
<table:table-cell office:value-type="time" office:time-value="14:30:00"/>
</table:table-row>
</table:table></office:spreadsheet></office:body></office:document-content>"#;
let book = zip(&[("mimetype", "application/vnd.oasis.opendocument.spreadsheet"), ("content.xml", content)]);
let (_, rows) = read_rows(&book, Pick::Index(0)).unwrap();
assert_eq!(rows.len(), 1);
assert_eq!(rows[0], vec!["Hello", "0.15", "42", "14:30"]);
// XLSX with case-insensitive cell types
let sheet = r#"<worksheet><sheetData><row r="1">
<c r="A1" t="B"><v>1</v></c>
<c r="B1" t="INLINESTR"><is><t>World</t></is></c>
<c r="C1" t="S"><v>0</v></c>
</row></sheetData></worksheet>"#;
let (_, rows) = read_rows(&xlsx(sheet), Pick::Index(0)).unwrap();
assert_eq!(rows.len(), 1);
assert_eq!(rows[0], vec!["TRUE", "World", "Name"]);
}
}