Skip to content

clean up unicodedata #4567

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
youknowone merged 1 commit into from
Feb 25, 2023
Merged

clean up unicodedata #4567

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
72 changes: 48 additions & 24 deletions stdlib/src/unicodedata.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,10 @@
/* Access to the unicode database.
See also: https://docs.python.org/3/library/unicodedata.html
*/
use crate::vm::{PyObjectRef, PyPayload, VirtualMachine};
use crate::vm::{
builtins::PyStr, convert::TryFromBorrowedObject, PyObject, PyObjectRef, PyPayload, PyResult,
VirtualMachine,
};

pub fn make_module(vm: &VirtualMachine) -> PyObjectRef {
let module = unicodedata::make_module(vm);
Expand All @@ -28,6 +31,30 @@ pub fn make_module(vm: &VirtualMachine) -> PyObjectRef {
module
}

enum NormalizeForm {
Nfc,
Nfkc,
Nfd,
Nfkd,
}

impl TryFromBorrowedObject for NormalizeForm {
fn try_from_borrowed_object(vm: &VirtualMachine, obj: &PyObject) -> PyResult<Self> {
obj.try_value_with(
|form: &PyStr| {
Ok(match form.as_str() {
"NFC" => NormalizeForm::Nfc,
"NFKC" => NormalizeForm::Nfkc,
"NFD" => NormalizeForm::Nfd,
"NFKD" => NormalizeForm::Nfkd,
_ => return Err(vm.new_value_error("invalid normalization form".to_owned())),
})
},
vm,
)
}
}

#[pymodule]
mod unicodedata {
use crate::vm::{
Expand Down Expand Up @@ -63,11 +90,7 @@ mod unicodedata {
vm.new_type_error("argument must be an unicode character, not str".to_owned())
})?;

if self.check_age(c) {
Ok(Some(c))
} else {
Ok(None)
}
Ok(self.check_age(c).then_some(c))
}
}

Expand Down Expand Up @@ -112,40 +135,41 @@ mod unicodedata {
}

#[pymethod]
fn bidirectional(&self, character: PyStrRef, vm: &VirtualMachine) -> PyResult<String> {
fn bidirectional(
&self,
character: PyStrRef,
vm: &VirtualMachine,
) -> PyResult<&'static str> {
let bidi = match self.extract_char(character, vm)? {
Some(c) => BidiClass::of(c).abbr_name(),
None => "",
};
Ok(bidi.to_owned())
Ok(bidi)
}

/// NOTE: This function uses 9.0.0 database instead of 3.2.0
#[pymethod]
fn east_asian_width(&self, character: PyStrRef, vm: &VirtualMachine) -> PyResult<String> {
fn east_asian_width(
&self,
character: PyStrRef,
vm: &VirtualMachine,
) -> PyResult<&'static str> {
Ok(self
.extract_char(character, vm)?
.map_or(EastAsianWidth::Neutral, |c| c.east_asian_width())
.abbr_name()
.to_owned())
.abbr_name())
}

#[pymethod]
fn normalize(
&self,
form: PyStrRef,
unistr: PyStrRef,
vm: &VirtualMachine,
) -> PyResult<String> {
fn normalize(&self, form: super::NormalizeForm, unistr: PyStrRef) -> PyResult<String> {
use super::NormalizeForm::*;
let text = unistr.as_str();
let normalized_text = match form.as_str() {
"NFC" => text.nfc().collect::<String>(),
"NFKC" => text.nfkc().collect::<String>(),
"NFD" => text.nfd().collect::<String>(),
"NFKD" => text.nfkd().collect::<String>(),
_ => return Err(vm.new_value_error("invalid normalization form".to_owned())),
let normalized_text = match form {
Nfc => text.nfc().collect::<String>(),
Nfkc => text.nfkc().collect::<String>(),
Nfd => text.nfd().collect::<String>(),
Nfkd => text.nfkd().collect::<String>(),
};

Ok(normalized_text)
}

Expand Down