Skip to content

Remove unused XPath functions min, max, ReplaceAll, FontSizeGuess #906

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

Draft
moritz-gross wants to merge 4 commits into
base: main
Choose a base branch
from
Draft

Remove unused XPath functions min, max, ReplaceAll, FontSizeGuess #906

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
283081e
Remove unused XPath functions min, max, ReplaceAll, FontSizeGuess
moritz-gross Oct 24, 2026
445a4de
Merge branch 'main' into remove-unused-xpath-functions
moritz-gross Oct 26, 2026
f92f27c
Merge branch 'main' into remove-unused-xpath-functions
moritz-gross Oct 26, 2026
42aebff
Use lazy-regex for static regex in `em_from_value`
moritz-gross Oct 26, 2026
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
2 changes: 1 addition & 1 deletion src/canonicalize.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1136,7 +1136,7 @@ impl CanonicalizeContext {
// normalize width ems
let width_raw = mathml.attribute_value("width");
let width = width_raw.as_deref().unwrap_or("0em");
let normalized_width = crate::xpath_functions::FontSizeGuess::em_from_value(width);
let normalized_width = crate::xpath_functions::em_from_value(width);
mathml.set_attribute_value("data-width", &normalized_width.to_string());
return Some(mathml);
},
Expand Down
165 changes: 40 additions & 125 deletions src/xpath_functions.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -649,45 +649,6 @@ impl Function for ToCommonFraction {
}
}

struct Min;
/**
* Returns true the smallest of the two args
* @param(num1)
* @param(num2)
*/
impl Function for Min {

fn evaluate<'d>(&self,
_context: &context::Evaluation<'_, 'd>,
args: Vec<Value<'d>>)
-> Result<Value<'d>, Error>
{
let mut args = Args(args);
args.exactly(2)?;
let num1 = args.pop_number()?;
let num2 = args.pop_number()?;
return Ok( Value::Number( num1.min(num2) ) );
}
}

struct Max;

impl Function for Max {

fn evaluate<'d>(&self,
_context: &context::Evaluation<'_, 'd>,
args: Vec<Value<'d>>)
-> Result<Value<'d>, Error>
{
let mut args = Args(args);
args.exactly(2)?;
let num1 = args.pop_number()?;
let num2 = args.pop_number()?;
return Ok( Value::Number( num1.max(num2) ) );
}
}


struct BaseNode;
/**
* Returns the base of a scripted element (msub, msup, munder, ...), looking through nested scripts
Expand Down Expand Up @@ -1350,83 +1311,43 @@ impl Function for GetNavigationPartName {
}
}

pub struct FontSizeGuess;
/// FontSizeGuess(size_string)
/// returns a guess of the size in "ems"
/// Examples:
/// "0.278em" -> 0.278
/// ""
// returns original node match isn't found
impl FontSizeGuess {
/// Returns an estimated width in em units, using an assumed 12-point font for conversions.
pub fn em_from_value(value_with_unit: &str) -> f64 {
// match one or more digits followed by a unit -- there are many more units, but they tend to be large and rarer(?)
static FONT_VALUE: Lazy<Regex> = lazy_regex!(r"(-?[0-9]*\.?[0-9]*)(px|cm|mm|Q|in|pc|pt|ex|em|rem)");
let cap = FONT_VALUE.captures(value_with_unit);
if let Some(cap) = cap {
if cap.len() == 3 {
let multiplier = match &cap[2] { // guess based on 12pt font to convert to ems
"px" => 1.0/12.0,
"cm" => 2.37,
"mm" => 0.237,
"Q" => 0.059, // 1/4 mm
"in" => 6.02,
"pc" => 1.0,
"pt" => 1.0/12.0,
"ex" => 0.5,
"em" => 1.0,
"rem" => 16.0/12.0,
default => {debug!("unit='{default}'"); 10.0}
};
// debug!("FontSizeGuess: {}->{}, val={}, multiplier={}", value_with_unit, value*multiplier, value, multiplier);
return cap[1].parse::<f64>().unwrap_or(0.0) * multiplier;
} else {
return 0.0; // something bad happened
}
}else {
let multiplier = match value_with_unit { // guess based on 12pt font to convert to ems
"veryverythinspace" => 1.0/18.0,
"verythinspace" => 2.0/18.0,
"thinspace" => 3.0/18.0,
"mediumspace" => 4.0/18.0,
"thickspace" => 5.0/18.0,
"verythickspace" => 6.0/18.0,
"veryverythickspace" => 7.0/18.0,
_ => 0.0,
/// Converts a MathML length (e.g. "0.278em", "12pt", "thinspace") to an estimated size in ems, assuming a 12-point font.
pub(crate) fn em_from_value(value_with_unit: &str) -> f64 {
// match one or more digits followed by a unit -- there are many more units, but they tend to be large and rarer(?)
static FONT_VALUE: Lazy<Regex> = lazy_regex!(r"(-?[0-9]*\.?[0-9]*)(px|cm|mm|Q|in|pc|pt|ex|em|rem)");
let cap = FONT_VALUE.captures(value_with_unit);
if let Some(cap) = cap {
if cap.len() == 3 {
let multiplier = match &cap[2] { // guess based on 12pt font to convert to ems
"px" => 1.0/12.0,
"cm" => 2.37,
"mm" => 0.237,
"Q" => 0.059, // 1/4 mm
"in" => 6.02,
"pc" => 1.0,
"pt" => 1.0/12.0,
"ex" => 0.5,
"em" => 1.0,
"rem" => 16.0/12.0,
default => {debug!("unit='{default}'"); 10.0}
};
return multiplier;
// debug!("em_from_value: {}->{}, val={}, multiplier={}", value_with_unit, value*multiplier, value, multiplier);
return cap[1].parse::<f64>().unwrap_or(0.0) * multiplier;
} else {
return 0.0; // something bad happened
}
}
}
impl Function for FontSizeGuess {
fn evaluate<'d>(&self,
_context: &context::Evaluation<'_, 'd>,
args: Vec<Value<'d>>)
-> Result<Value<'d>, Error>
{
let mut args = Args(args);
args.exactly(1)?;
let value_with_unit = args.pop_string()?;
let em_value = FontSizeGuess::em_from_value(&value_with_unit);
return Ok( Value::Number(em_value) );
}
}

pub struct ReplaceAll;
/// ReplaceAll(haystack, needle, replacement)
/// Returns a string with all occurrences of 'needle' replaced with 'replacement'
impl Function for ReplaceAll {
fn evaluate<'d>(&self,
_context: &context::Evaluation<'_, 'd>,
args: Vec<Value<'d>>)
-> Result<Value<'d>, Error>
{
let mut args = Args(args);
args.exactly(3)?;
let replacement = args.pop_string()?;
let needle = args.pop_string()?;
let haystack = args.pop_string()?;
return Ok( Value::String(haystack.replace(&needle, &replacement)) );
}else {
let multiplier = match value_with_unit { // guess based on 12pt font to convert to ems
"veryverythinspace" => 1.0/18.0,
"verythinspace" => 2.0/18.0,
"thinspace" => 3.0/18.0,
"mediumspace" => 4.0/18.0,
"thickspace" => 5.0/18.0,
"verythickspace" => 6.0/18.0,
"veryverythickspace" => 7.0/18.0,
_ => 0.0,
};
return multiplier;
}
}

Expand Down Expand Up @@ -1702,12 +1623,6 @@ pub fn register_mathcat_xpath_functions(context: &mut Context) {
context.set_function("HasVisibleColumnLine", HasVisibleColumnLine);
context.set_function("HasVisibleRowLine", HasVisibleRowLine);
context.set_function("DEBUG", Debug);

// Not used: remove??
context.set_function("min", Min); // missing in xpath 1.0
context.set_function("max", Max); // missing in xpath 1.0
context.set_function("FontSizeGuess", FontSizeGuess);
context.set_function("ReplaceAll", ReplaceAll);
}


Expand Down Expand Up @@ -1738,11 +1653,11 @@ mod tests {
// Pica widths must use the existing 12pt font estimate: 1pc, 12pt, and 1em are equivalent.
#[test]
fn font_size_guess_pica_widths() {
assert_eq!(FontSizeGuess::em_from_value("1pc"), 1.0);
assert_eq!(FontSizeGuess::em_from_value("0.5pc"), 0.5);
assert_eq!(FontSizeGuess::em_from_value("-1pc"), -1.0);
assert_eq!(FontSizeGuess::em_from_value("12pt"), 1.0);
assert_eq!(FontSizeGuess::em_from_value("1em"), 1.0);
assert_eq!(em_from_value("1pc"), 1.0);
assert_eq!(em_from_value("0.5pc"), 0.5);
assert_eq!(em_from_value("-1pc"), -1.0);
assert_eq!(em_from_value("12pt"), 1.0);
assert_eq!(em_from_value("1em"), 1.0);
}

#[test]
Expand Down
Loading