1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286
use std::collections::HashMap;
use super::html_scanner::TokenType;
#[derive(Debug, Clone)]
pub struct Node {
/// It's None only when new
pub tag: Option<String>,
pub start: usize,
pub end: usize,
pub children: Vec<Node>,
/// Whether part of end tag exists
pub closed: bool,
/// It's None only when new, it larger than end of start tag
pub start_tag_end: Option<usize>,
/// It's None only when it's self-closing tag or it miss part of end tag, it equals start of end tag
pub end_tag_start: Option<usize>,
pub attributes: HashMap<String, NodeAttribute>,
}
#[derive(Debug, Clone, PartialEq)]
pub struct NodeAttribute {
/// include quote
pub value: Option<String>,
/// start offset of attribute name
pub offset: usize,
}
impl NodeAttribute {
pub fn new(value: Option<String>, offset: usize) -> NodeAttribute {
NodeAttribute { value, offset }
}
}
impl Node {
pub fn new(start: usize, end: usize, children: Vec<Node>) -> Node {
Node {
tag: None,
start,
end,
children,
closed: false,
start_tag_end: None,
end_tag_start: None,
attributes: HashMap::new(),
}
}
pub fn attribute_names(&self) -> Vec<&String> {
self.attributes.keys().collect()
}
pub fn attribute_names_by_order(&self) -> Vec<&String> {
let mut attributes = self.attribute_names();
attributes.sort_by(|a, b| {
let a = self.attributes.get(*a).unwrap().offset;
let b = self.attributes.get(*b).unwrap().offset;
a.cmp(&b)
});
attributes
}
pub fn is_self_closing(&self) -> bool {
self.end_tag_start.is_none()
}
pub fn is_same_tag(&self, tag_in_lowercase: Option<&str>) -> bool {
if self.tag.is_none() {
tag_in_lowercase.is_none()
} else {
let tag: &str = &self.tag.as_ref().unwrap();
tag_in_lowercase.is_some_and(|tag_in_lowercase| {
tag.len() == tag_in_lowercase.len() && tag.to_lowercase() == tag_in_lowercase
})
}
}
pub fn first_child(&self) -> Option<&Node> {
Some(self.children.first()?)
}
pub fn last_child(&self) -> Option<&Node> {
Some(self.children.last()?)
}
pub fn find_node_before<'a>(
node: &'a Node,
offset: usize,
parent_list: &mut Vec<&'a Node>,
) -> &'a Node {
let mut idx = node.children.len();
for (i, child) in node.children.iter().enumerate() {
if offset <= child.start {
idx = i;
break;
}
}
if idx > 0 {
let child = &node.children[idx - 1];
if offset > child.start {
if offset < child.end {
parent_list.push(&node);
return Node::find_node_before(child, offset, parent_list);
}
if let Some(last_child) = child.last_child() {
if last_child.end == child.end {
parent_list.push(&node);
return Node::find_node_before(child, offset, parent_list);
}
}
parent_list.push(&node);
return child;
}
}
node
}
pub fn find_node_at<'a>(
node: &'a Node,
offset: usize,
parent_list: &mut Vec<&'a Node>,
) -> &'a Node {
let mut idx = node.children.len();
for (i, child) in node.children.iter().enumerate() {
if offset < child.start {
idx = i;
break;
}
}
if idx > 0 {
let child = &node.children[idx - 1];
if offset >= child.start && offset < child.end {
parent_list.push(&node);
return Node::find_node_at(child, offset, parent_list);
}
}
node
}
/// Find TokenType in node at offset
///
/// it return StartTagOpen, StartTag, StartTagClose, StartTagSelfClose, Content, EndTagOpen, EndTag, EndTagClose, Unknown
///
/// if offset in children, then it's Content
/// if offset outside of node then it's Unknown
pub fn find_token_type_in_node(node: &Node, offset: usize) -> TokenType {
if node.start > offset || node.end <= offset {
return TokenType::Unknown;
}
let tag = node.tag.as_ref().unwrap();
if node.start == offset {
return TokenType::StartTagOpen;
}
if offset < node.start + 1 + tag.len() {
return TokenType::StartTag;
}
let start_tag_end = *node.start_tag_end.as_ref().unwrap();
if offset >= start_tag_end {
if let Some(end_tag_start) = node.end_tag_start {
if offset < end_tag_start {
return TokenType::Content;
} else if offset == end_tag_start || offset == end_tag_start + 1 {
return TokenType::EndTagOpen;
} else if offset < node.end - 1 {
return TokenType::EndTag;
} else {
return TokenType::EndTagClose;
}
} else if start_tag_end == node.end {
if offset >= node.end - 2 {
return TokenType::StartTagSelfClose;
}
}
} else {
if start_tag_end == node.end {
if offset >= start_tag_end - 2 {
return TokenType::StartTagSelfClose;
}
} else {
if offset >= start_tag_end - 1 {
return TokenType::StartTagClose;
}
}
}
TokenType::Unknown
}
}
/// A tree of nodes for an HTML document
///
/// There is no reference to the parent node in the Node.
/// The associated functions `find_node_before` and `find_node_at` keep a record of all parents of the target node.
/// To get the parent node of the target node, you can like this:
///
/// ```rust
/// use html_languageservice::{parse_html_document, HTMLDataManager};
///
/// let html_document = parse_html_document("<div><h1>title</h1></div>", "html", &HTMLDataManager::default());
///
/// let mut parent_list = vec![];
/// let node = html_document.find_node_at(9, &mut parent_list);
/// assert_eq!(node.unwrap().tag, Some("h1".to_string()));
///
/// let parent = parent_list.pop();
/// assert_eq!(parent.unwrap().tag, Some("div".to_string()));
///
/// let parent = parent_list.pop();
/// assert!(parent.is_none());
/// ```
///
/// If 'parent' is 'None', then its parent node is HTMLDocument.
#[derive(Clone)]
pub struct HTMLDocument {
pub roots: Vec<Node>,
}
impl HTMLDocument {
/// Find the node before the node where the given 'offset' is located
///
/// `parent_list` is a list of parent nodes and the previous node is the parent node of the latter node.
/// If you don't care about the parent node, you can use `&mut vec![]`.
pub fn find_node_before<'a>(
&'a self,
offset: usize,
parent_list: &mut Vec<&'a Node>,
) -> Option<&'a Node> {
let mut idx = self.roots.len();
for (i, child) in self.roots.iter().enumerate() {
if offset <= child.start {
idx = i;
break;
}
}
if idx > 0 {
let child = &self.roots[idx - 1];
if offset > child.start {
if offset < child.end {
return Some(Node::find_node_before(child, offset, parent_list));
}
if let Some(last_child) = child.last_child() {
if last_child.end == child.end {
return Some(Node::find_node_before(child, offset, parent_list));
}
}
return Some(child);
}
}
None
}
/// Find the node at the given 'offset' location
///
/// `parent_list` is a list where the previous node is the parent node of the latter node.
/// If you don't care about the parent node, you can use `&mut vec![]`.
pub fn find_node_at<'a>(
&'a self,
offset: usize,
parent_list: &mut Vec<&'a Node>,
) -> Option<&'a Node> {
let mut idx = self.roots.len();
for (i, child) in self.roots.iter().enumerate() {
if offset < child.start {
idx = i;
break;
}
}
if idx > 0 {
let child = &self.roots[idx - 1];
if offset >= child.start && offset < child.end {
return Some(Node::find_node_at(child, offset, parent_list));
}
}
None
}
pub fn find_root_at(&self, offset: usize) -> Option<&Node> {
for root in &self.roots {
if offset <= root.end {
return Some(root);
}
}
None
}
}