Skip to content

Bump selectors, cssparser and html5ever #214

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.

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
merged 2 commits into from
Oct 24, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
52 changes: 17 additions & 35 deletions Cargo.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

11 changes: 6 additions & 5 deletions scraper/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -13,13 +13,14 @@ repository = "https://github.com/causal-agent/scraper"
readme = "README.md"

[dependencies]
cssparser = "0.31.0"
ahash = "0.8.0"
cssparser = "0.34.0"
ego-tree = "0.9.0"
html5ever = "0.27"
selectors = "0.25.0"
tendril = "0.4.3"
ahash = "0.8"
html5ever = "0.29.0"
indexmap = { version = "2.6.0", optional = true }
precomputed-hash = "0.1.1"
selectors = "0.26.0"
tendril = "0.4.3"

[dependencies.getopts]
version = "0.2.21"
Expand Down
10 changes: 10 additions & 0 deletions scraper/src/element_ref/element.rs
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
use html5ever::Namespace;
use selectors::{
attr::{AttrSelectorOperation, CaseSensitivity, NamespaceConstraint},
bloom::BloomFilter,
matching, Element, OpaqueElement,
};

Expand Down Expand Up @@ -122,6 +123,10 @@ impl<'a> Element for ElementRef<'a> {
self.value().has_class(&name.0, case_sensitivity)
}

fn has_custom_state(&self, _name: &CssLocalName) -> bool {
false
}

fn is_empty(&self) -> bool {
!self
.children()
Expand All @@ -134,6 +139,11 @@ impl<'a> Element for ElementRef<'a> {
}

fn apply_selector_flags(&self, _flags: matching::ElementSelectorFlags) {}

fn add_element_unique_hashes(&self, _filter: &mut BloomFilter) -> bool {
// FIXME: Do we want to add `self.node.id()` here?
false
}
}

#[cfg(test)]
Expand Down
12 changes: 6 additions & 6 deletions scraper/src/element_ref/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ use std::ops::Deref;
use ego_tree::iter::{Edge, Traverse};
use ego_tree::NodeRef;
use html5ever::serialize::{serialize, SerializeOpts, TraversalScope};
use selectors::NthIndexCache;
use selectors::matching::SelectorCaches;

use crate::node::Element;
use crate::{Node, Selector};
Expand Down Expand Up @@ -49,7 +49,7 @@ impl<'a> ElementRef<'a> {
scope: *self,
inner,
selector,
nth_index_cache: NthIndexCache::default(),
caches: Default::default(),
}
}

Expand Down Expand Up @@ -135,7 +135,7 @@ pub struct Select<'a, 'b> {
scope: ElementRef<'a>,
inner: Traverse<'a, Node>,
selector: &'b Selector,
nth_index_cache: NthIndexCache,
caches: SelectorCaches,
}

impl Debug for Select<'_, '_> {
Expand All @@ -144,7 +144,7 @@ impl Debug for Select<'_, '_> {
.field("scope", &self.scope)
.field("inner", &self.inner)
.field("selector", &self.selector)
.field("nth_index_cache", &"..")
.field("caches", &"..")
.finish()
}
}
Expand All @@ -155,7 +155,7 @@ impl Clone for Select<'_, '_> {
scope: self.scope,
inner: self.inner.clone(),
selector: self.selector,
nth_index_cache: NthIndexCache::default(),
caches: Default::default(),
}
}
}
Expand All @@ -170,7 +170,7 @@ impl<'a, 'b> Iterator for Select<'a, 'b> {
if self.selector.matches_with_scope_and_cache(
&element,
Some(self.scope),
&mut self.nth_index_cache,
&mut self.caches,
) {
return Some(element);
}
Expand Down
37 changes: 18 additions & 19 deletions scraper/src/html/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -10,12 +10,14 @@ use ego_tree::Tree;
use html5ever::serialize::SerializeOpts;
use html5ever::tree_builder::QuirksMode;
use html5ever::{driver, serialize, QualName};
use selectors::NthIndexCache;
use selectors::matching::SelectorCaches;
use tendril::TendrilSink;

use crate::selector::Selector;
use crate::{ElementRef, Node};

pub use tree_sink::HtmlTreeSink;

/// An HTML tree.
///
/// Parsing does not fail hard. Instead, the `quirks_mode` is set and errors are added to the
Expand Down Expand Up @@ -67,22 +69,23 @@ impl Html {
/// # fn main() {
/// # let document = "";
/// use html5ever::driver::{self, ParseOpts};
/// use scraper::Html;
/// use scraper::{Html, HtmlTreeSink};
/// use tendril::TendrilSink;
///
/// let parser = driver::parse_document(Html::new_document(), ParseOpts::default());
/// let parser = driver::parse_document(HtmlTreeSink::new(Html::new_document()), ParseOpts::default());
/// let html = parser.one(document);
/// # }
/// ```
pub fn parse_document(document: &str) -> Self {
let parser = driver::parse_document(Self::new_document(), Default::default());
let parser =
driver::parse_document(HtmlTreeSink::new(Self::new_document()), Default::default());
parser.one(document)
}

/// Parses a string of HTML as a fragment.
pub fn parse_fragment(fragment: &str) -> Self {
let parser = driver::parse_fragment(
Self::new_fragment(),
HtmlTreeSink::new(Self::new_fragment()),
Default::default(),
QualName::new(None, ns!(html), local_name!("body")),
Vec::new(),
Expand All @@ -95,7 +98,7 @@ impl Html {
Select {
inner: self.tree.nodes(),
selector,
nth_index_cache: NthIndexCache::default(),
caches: Default::default(),
}
}

Expand Down Expand Up @@ -127,15 +130,15 @@ impl Html {
pub struct Select<'a, 'b> {
inner: Nodes<'a, Node>,
selector: &'b Selector,
nth_index_cache: NthIndexCache,
caches: SelectorCaches,
}

impl fmt::Debug for Select<'_, '_> {
fn fmt(&self, fmt: &mut fmt::Formatter<'_>) -> fmt::Result {
fmt.debug_struct("Select")
.field("inner", &self.inner)
.field("selector", &self.selector)
.field("nth_index_cache", &"..")
.field("caches", &"..")
.finish()
}
}
Expand All @@ -145,7 +148,7 @@ impl Clone for Select<'_, '_> {
Self {
inner: self.inner.clone(),
selector: self.selector,
nth_index_cache: NthIndexCache::default(),
caches: Default::default(),
}
}
}
Expand All @@ -157,11 +160,9 @@ impl<'a, 'b> Iterator for Select<'a, 'b> {
for node in self.inner.by_ref() {
if let Some(element) = ElementRef::wrap(node) {
if element.parent().is_some()
&& self.selector.matches_with_scope_and_cache(
&element,
None,
&mut self.nth_index_cache,
)
&& self
.selector
.matches_with_scope_and_cache(&element, None, &mut self.caches)
{
return Some(element);
}
Expand All @@ -182,11 +183,9 @@ impl<'a, 'b> DoubleEndedIterator for Select<'a, 'b> {
for node in self.inner.by_ref().rev() {
if let Some(element) = ElementRef::wrap(node) {
if element.parent().is_some()
&& self.selector.matches_with_scope_and_cache(
&element,
None,
&mut self.nth_index_cache,
)
&& self
.selector
.matches_with_scope_and_cache(&element, None, &mut self.caches)
{
return Some(element);
}
Expand Down
Loading
Loading