Skip to content
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

Jump to bottom

Introduce Config struct that holds parser configuration and implement #513 #677

Merged
merged 11 commits into from
Nov 5, 2023
Merged

Introduce Config struct that holds parser configuration and implement #513 #677

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
47f3638
Add explicit tests for `expand_empty_elements` reader option
Mingun Oct 29, 2023
27cb615
Add explicit tests for `trim_text` reader option
Mingun Oct 29, 2023
d58c8bc
Add explicit tests for `trim_text_end` reader option
Mingun Oct 29, 2023
4176571
Add explicit tests for `trim_markup_names_in_closing_tags` reader option
Mingun Oct 29, 2023
86ccc0a
Add explicit tests for `check_end_names` reader option
Mingun Nov 3, 2023
7980448
#513: Allow to continue parsing after `Error::IllFormed`
Mingun Nov 3, 2023
475a883
Add explicit tests for `check_comments` reader option
Mingun Nov 3, 2023
8101e29
Introduce `.config()` and `.config_mut()` and replace builder methods…
Mingun Nov 6, 2022
77af4b3
Set the whole reader config in fuzzing tests
Mingun Nov 4, 2023
75b4028
Sort options (mostly) alphabetically
Mingun Nov 3, 2023
3875bdb
Add explicit tests for `trim_text_start` reader option
Mingun Nov 4, 2023
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
175 changes: 175 additions & 0 deletions tests/reader-config.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,175 @@
//! Contains tests for config options of a parser.
//!
//! Each module has a name of a corresponding option and functions inside performs
//! testing of various option values.
//!
//! Please keep tests sorted (exceptions are allowed if options are tightly related).

use quick_xml::events::{BytesCData, BytesEnd, BytesStart, BytesText, Event};
use quick_xml::reader::Reader;

mod expand_empty_elements {
use super::*;
use pretty_assertions::assert_eq;

/// Self-closed elements should be reported as one `Empty` event
#[test]
fn false_() {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Perhaps "enabled" and "disabled" would be better names, to avoid keyword clashes?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I chose those words because if we will have other options that are not booleans, tests would be named as a config value

let mut reader = Reader::from_str("<root/>");
reader.expand_empty_elements(false);

assert_eq!(
reader.read_event().unwrap(),
Event::Empty(BytesStart::new("root"))
);
assert_eq!(reader.read_event().unwrap(), Event::Eof);
}

/// Self-closed elements should be reported as two events
#[test]
fn true_() {
let mut reader = Reader::from_str("<root/>");
reader.expand_empty_elements(true);

assert_eq!(
reader.read_event().unwrap(),
Event::Start(BytesStart::new("root"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::End(BytesEnd::new("root"))
);
assert_eq!(reader.read_event().unwrap(), Event::Eof);
}
}

const XML: &str = " \t\r\n\
<!doctype root \t\r\n> \t\r\n\
<root \t\r\n> \t\r\n\
<empty \t\r\n/> \t\r\n\
text \t\r\n\
<!-- comment \t\r\n--> \t\r\n\
<![CDATA[ \t\r\ncdata \t\r\n]]> \t\r\n\
<?pi \t\r\n?> \t\r\n\
</root> \t\r\n";

mod trim_text {
use super::*;
use pretty_assertions::assert_eq;

#[test]
fn false_() {
let mut reader = Reader::from_str(XML);
reader.trim_text(false);

assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new(" \t\r\n"))
);

assert_eq!(
reader.read_event().unwrap(),
Event::DocType(BytesText::new("root \t\r\n"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new(" \t\r\n"))
);

assert_eq!(
reader.read_event().unwrap(),
Event::Start(BytesStart::from_content("root \t\r\n", 4))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new(" \t\r\n"))
);

assert_eq!(
reader.read_event().unwrap(),
Event::Empty(BytesStart::from_content("empty \t\r\n", 5))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new(" \t\r\ntext \t\r\n"))
);

assert_eq!(
reader.read_event().unwrap(),
Event::Comment(BytesText::new(" comment \t\r\n"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new(" \t\r\n"))
);

assert_eq!(
reader.read_event().unwrap(),
Event::CData(BytesCData::new(" \t\r\ncdata \t\r\n"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new(" \t\r\n"))
);

assert_eq!(
reader.read_event().unwrap(),
Event::PI(BytesText::new("pi \t\r\n"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new(" \t\r\n"))
);

assert_eq!(
reader.read_event().unwrap(),
Event::End(BytesEnd::new("root"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new(" \t\r\n"))
);

assert_eq!(reader.read_event().unwrap(), Event::Eof);
}

#[test]
fn true_() {
let mut reader = Reader::from_str(XML);
reader.trim_text(true);

assert_eq!(
reader.read_event().unwrap(),
Event::DocType(BytesText::new("root \t\r\n"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Start(BytesStart::from_content("root \t\r\n", 4))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Empty(BytesStart::from_content("empty \t\r\n", 5))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Text(BytesText::new("text"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::Comment(BytesText::new(" comment \t\r\n"))
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we have any reason to support trimming the text values of "comments"? I cannot immediately think of a reason to do that, but perhaps one exists.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think not, at least nobody request such feature. If such a request appears, we can add a separate option.

Generally speaking, I would delete the current trim options as they simply do not work correctly for text alternating with CDATA / comments / processing instructions, but I suppose that would break many users. I was thinking about renaming current Event into RawEvent and DeEvent to Event and give users stream of Events. The RawEvent then would be a low-level event which usually not needed by most users. That is very raw thoughts currently, so I decided to not do revolutional changes for now.

);
assert_eq!(
reader.read_event().unwrap(),
Event::CData(BytesCData::new(" \t\r\ncdata \t\r\n"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::PI(BytesText::new("pi \t\r\n"))
);
assert_eq!(
reader.read_event().unwrap(),
Event::End(BytesEnd::new("root"))
);
assert_eq!(reader.read_event().unwrap(), Event::Eof);
}
}
21 changes: 0 additions & 21 deletions tests/test.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,17 +88,6 @@ fn test_comment_starting_with_gt() {
}
}

#[test]
fn test_no_trim() {
let mut reader = Reader::from_str(" <tag> text </tag> ");

assert!(matches!(reader.read_event().unwrap(), Text(_)));
assert!(matches!(reader.read_event().unwrap(), Start(_)));
assert!(matches!(reader.read_event().unwrap(), Text(_)));
assert!(matches!(reader.read_event().unwrap(), End(_)));
assert!(matches!(reader.read_event().unwrap(), Text(_)));
}

#[test]
fn test_trim_end() {
let mut reader = Reader::from_str(" <tag> text </tag> ");
Expand All @@ -110,16 +99,6 @@ fn test_trim_end() {
assert!(matches!(reader.read_event().unwrap(), End(_)));
}

#[test]
fn test_trim() {
let mut reader = Reader::from_str(" <tag> text </tag> ");
reader.trim_text(true);

assert!(matches!(reader.read_event().unwrap(), Start(_)));
assert!(matches!(reader.read_event().unwrap(), Text(_)));
assert!(matches!(reader.read_event().unwrap(), End(_)));
}

#[test]
fn test_clone_reader() {
let mut reader = Reader::from_str("<tag>text</tag>");
Expand Down
25 changes: 0 additions & 25 deletions tests/unit_tests.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,20 +81,6 @@ fn test_start_end_attr() {
next_eq!(r, Start, b"a", End, b"a");
}

#[test]
fn test_empty() {
let mut r = Reader::from_str("<a />");
r.trim_text(true);
next_eq!(r, Empty, b"a");
}

#[test]
fn test_empty_can_be_expanded() {
let mut r = Reader::from_str("<a />");
r.trim_text(true).expand_empty_elements(true);
next_eq!(r, Start, b"a", End, b"a");
}

#[test]
fn test_empty_attr() {
let mut r = Reader::from_str("<a b=\"test\" />");
Expand Down Expand Up @@ -157,17 +143,6 @@ fn test_xml_decl() {
}
}

#[test]
fn test_trim_test() {
let txt = "<a><b> </b></a>";
let mut r = Reader::from_str(txt);
r.trim_text(true);
next_eq!(r, Start, b"a", Start, b"b", End, b"b", End, b"a");

let mut r = Reader::from_str(txt);
next_eq!(r, Start, b"a", Start, b"b", Text, b" ", End, b"b", End, b"a");
}

#[test]
fn test_cdata() {
let mut r = Reader::from_str("<![CDATA[test]]>");
Expand Down