Initialize logger for rcdom examples, cleanup html5ever a bit (#596)

* Initialize env logger for examples

Signed-off-by: Simon Wülker <simon.wuelker@arcor.de>

* Rename a couple methods, add spec comments

Signed-off-by: Simon Wülker <simon.wuelker@arcor.de>

* Fix lint errors

Signed-off-by: Simon Wülker <simon.wuelker@arcor.de>

---------

Signed-off-by: Simon Wülker <simon.wuelker@arcor.de>

Author: simonwuelker

html5ever/src/tokenizer/mod.rs

@@ -1616,7 +1616,7 @@ mod test {
         }
 
         fn finish_str(&self) {
-            if self.current_str.borrow().len() > 0 {
+            if !self.current_str.borrow().is_empty() {
                 let s = self.current_str.take();
                 self.tokens.borrow_mut().push(CharacterTokens(s));
             }

html5ever/src/tree_builder/mod.rs

@@ -947,29 +947,51 @@ where
         }
     }
 
-    /// Reconstruct the active formatting elements.
-    fn reconstruct_formatting(&self) {
+    /// <https://html.spec.whatwg.org/#reconstruct-the-active-formatting-elements>
+    fn reconstruct_active_formatting_elements(&self) {
         {
             let active_formatting = self.active_formatting.borrow();
-            let last = unwrap_or_return!(active_formatting.last());
+
+            // Step 1. If there are no entries in the list of active formatting elements,
+            // then there is nothing to reconstruct; stop this algorithm.
+            let Some(last) = active_formatting.last() else {
+                return;
+            };
+
+            // Step 2. If the last (most recently added) entry in the list of active formatting elements is a marker,
+            // or if it is an element that is in the stack of open elements, then there is nothing to reconstruct;
+            // stop this algorithm.
             if self.is_marker_or_open(last) {
                 return;
             }
         }
 
+        // Step 3. Let entry be the last (most recently added) element in the list of active formatting elements.
+        // NOTE: We track the index of the element instead
         let mut entry_index = self.active_formatting.borrow().len() - 1;
         loop {
+            // Step 4. Rewind: If there are no entries before entry in the list of active formatting elements,
+            // then jump to the step labeled create.
             if entry_index == 0 {
                 break;
             }
+
+            // Step 5. Let entry be the entry one earlier than entry in the list of active formatting elements.
             entry_index -= 1;
+
+            // Step 6. If entry is neither a marker nor an element that is also in the stack of open elements,
+            // go to the step labeled rewind.
+            // Step 7. Advance: Let entry be the element one later than entry in the list
+            // of active formatting elements.
             if self.is_marker_or_open(&self.active_formatting.borrow()[entry_index]) {
                 entry_index += 1;
                 break;
             }
         }
 
         loop {
+            // Step 8. Create: Insert an HTML element for the token for which the element entry was created,
+            // to obtain new element.
             let tag = match self.active_formatting.borrow()[entry_index] {
                 FormatEntry::Element(_, ref t) => t.clone(),
                 FormatEntry::Marker => {
@@ -985,8 +1007,13 @@ where
                 tag.name.clone(),
                 tag.attrs.clone(),
             );
+
+            // Step 9. Replace the entry for entry in the list with an entry for new element.
             self.active_formatting.borrow_mut()[entry_index] =
                 FormatEntry::Element(new_element, tag);
+
+            // Step 10. If the entry for new element in the list of active formatting elements is
+            // not the last entry in the list, return to the step labeled advance.
             if entry_index == self.active_formatting.borrow().len() - 1 {
                 break;
             }
@@ -1091,15 +1118,17 @@ where
         self.in_scope(scope, |elem| self.html_elem_named(&elem, name.clone()))
     }
 
-    //§ closing-elements-that-have-implied-end-tags
-    fn generate_implied_end<TagSet>(&self, set: TagSet)
+    /// <https://html.spec.whatwg.org/#generate-implied-end-tags>
+    fn generate_implied_end_tags<TagSet>(&self, set: TagSet)
     where
         TagSet: Fn(ExpandedName) -> bool,
     {
         loop {
             {
                 let open_elems = self.open_elems.borrow();
-                let elem = unwrap_or_return!(open_elems.last());
+                let Some(elem) = open_elems.last() else {
+                    return;
+                };
                 let elem_name = self.sink.elem_name(elem);
                 if !set(elem_name.expanded()) {
                     return;
@@ -1110,7 +1139,7 @@ where
     }
 
     fn generate_implied_end_except(&self, except: LocalName) {
-        self.generate_implied_end(|p| {
+        self.generate_implied_end_tags(|p| {
             if *p.ns == ns!(html) && *p.local == except {
                 false
             } else {
@@ -1155,8 +1184,8 @@ where
         self.pop_until(|p| *p.ns == ns!(html) && *p.local == name)
     }
 
-    // Pop elements until one with the specified name has been popped.
-    // Signal an error if it was not the first one.
+    /// Pop elements until one with the specified name has been popped.
+    /// Signal an error if it was not the first one.
     fn expect_to_close(&self, name: LocalName) {
         if self.pop_until_named(name.clone()) != 1 {
             self.sink.parse_error(format_if!(
@@ -1170,7 +1199,7 @@ where
 
     fn close_p_element(&self) {
         declare_tag_set!(implied = [cursory_implied_end] - "p");
-        self.generate_implied_end(implied);
+        self.generate_implied_end_tags(implied);
         self.expect_to_close(local_name!("p"));
     }
 
@@ -1278,7 +1307,7 @@ where
     }
 
     fn close_the_cell(&self) {
-        self.generate_implied_end(cursory_implied_end);
+        self.generate_implied_end_tags(cursory_implied_end);
         if self.pop_until(td_th) != 1 {
             self.sink
                 .parse_error(Borrowed("expected to close <td> or <th> with cell"));

html5ever/src/tree_builder/rules.rs

@@ -190,7 +190,7 @@ where
                     if !self.in_html_elem_named(local_name!("template")) {
                         self.unexpected(&tag);
                     } else {
-                        self.generate_implied_end(thorough_implied_end);
+                        self.generate_implied_end_tags(thorough_implied_end);
                         self.expect_to_close(local_name!("template"));
                         self.clear_active_formatting_to_marker();
                         self.template_modes.borrow_mut().pop();
@@ -287,7 +287,7 @@ where
                 Token::NullCharacter => self.unexpected(&token),
 
                 Token::Characters(_, text) => {
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     if any_not_whitespace(&text) {
                         self.frameset_ok.set(false);
                     }
@@ -464,10 +464,10 @@ where
                 tag @ <button> => {
                     if self.in_scope_named(default_scope, local_name!("button")) {
                         self.sink.parse_error(Borrowed("nested buttons"));
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                         self.pop_until_named(local_name!("button"));
                     }
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     self.insert_element_for(tag);
                     self.frameset_ok.set(false);
                     ProcessResult::Done
@@ -480,7 +480,7 @@ where
                     if !self.in_scope_named(default_scope, tag.name.clone()) {
                         self.unexpected(&tag);
                     } else {
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                         self.expect_to_close(tag.name);
                     }
                     ProcessResult::Done
@@ -500,7 +500,7 @@ where
                             self.sink.parse_error(Borrowed("Form element not in scope on </form>"));
                             return ProcessResult::Done;
                         }
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                         let current = self.current_node().clone();
                         self.remove_from_stack(&node);
                         if !self.sink.same_node(&current, &node) {
@@ -511,7 +511,7 @@ where
                             self.sink.parse_error(Borrowed("Form element not in scope on </form>"));
                             return ProcessResult::Done;
                         }
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                         if !self.current_node_named(local_name!("form")) {
                             self.sink.parse_error(Borrowed("Bad open element on </form>"));
                         }
@@ -546,7 +546,7 @@ where
 
                 tag @ </h1> </h2> </h3> </h4> </h5> </h6> => {
                     if self.in_scope(default_scope, |n| self.elem_in(&n, heading_tag)) {
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                         if !self.current_node_named(tag.name) {
                             self.sink.parse_error(Borrowed("Closing wrong heading tag"));
                         }
@@ -559,23 +559,23 @@ where
 
                 tag @ <a> => {
                     self.handle_misnested_a_tags(&tag);
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     self.create_formatting_element_for(tag);
                     ProcessResult::Done
                 }
 
                 tag @ <b> <big> <code> <em> <font> <i> <s> <small> <strike> <strong> <tt> <u> => {
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     self.create_formatting_element_for(tag);
                     ProcessResult::Done
                 }
 
                 tag @ <nobr> => {
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     if self.in_scope_named(default_scope, local_name!("nobr")) {
                         self.sink.parse_error(Borrowed("Nested <nobr>"));
                         self.adoption_agency(local_name!("nobr"));
-                        self.reconstruct_formatting();
+                        self.reconstruct_active_formatting_elements();
                     }
                     self.create_formatting_element_for(tag);
                     ProcessResult::Done
@@ -588,7 +588,7 @@ where
                 }
 
                 tag @ <applet> <marquee> <object> => {
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     self.insert_element_for(tag);
                     self.active_formatting.borrow_mut().push(FormatEntry::Marker);
                     self.frameset_ok.set(false);
@@ -599,7 +599,7 @@ where
                     if !self.in_scope_named(default_scope, tag.name.clone()) {
                         self.unexpected(&tag);
                     } else {
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                         self.expect_to_close(tag.name);
                         self.clear_active_formatting_to_marker();
                     }
@@ -630,7 +630,7 @@ where
                         local_name!("input") => self.is_type_hidden(&tag),
                         _ => false,
                     };
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     self.insert_and_pop_element_for(tag);
                     if !keep_frameset_ok {
                         self.frameset_ok.set(false);
@@ -666,7 +666,7 @@ where
 
                 tag @ <xmp> => {
                     self.close_p_element_in_button_scope();
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     self.frameset_ok.set(false);
                     self.parse_raw_data(tag, Rawtext)
                 }
@@ -683,7 +683,7 @@ where
                 // <noscript> handled in wildcard case below
 
                 tag @ <select> => {
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     self.insert_element_for(tag);
                     self.frameset_ok.set(false);
                     // NB: mode == InBody but possibly self.mode != mode, if
@@ -700,14 +700,14 @@ where
                     if self.current_node_named(local_name!("option")) {
                         self.pop();
                     }
-                    self.reconstruct_formatting();
+                    self.reconstruct_active_formatting_elements();
                     self.insert_element_for(tag);
                     ProcessResult::Done
                 }
 
                 tag @ <rb> <rtc> => {
                     if self.in_scope_named(default_scope, local_name!("ruby")) {
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                     }
                     if !self.current_node_named(local_name!("ruby")) {
                         self.unexpected(&tag);
@@ -741,7 +741,7 @@ where
                     if self.opts.scripting_enabled && tag.name == local_name!("noscript") {
                         self.parse_raw_data(tag, Rawtext)
                     } else {
-                        self.reconstruct_formatting();
+                        self.reconstruct_active_formatting_elements();
                         self.insert_element_for(tag);
                         ProcessResult::Done
                     }
@@ -924,7 +924,7 @@ where
                 tag @ <caption> <col> <colgroup> <tbody> <td> <tfoot>
                   <th> <thead> <tr> </table> </caption> => {
                     if self.in_scope_named(table_scope, local_name!("caption")) {
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                         self.expect_to_close(local_name!("caption"));
                         self.clear_active_formatting_to_marker();
                         match tag {
@@ -1087,7 +1087,7 @@ where
             InsertionMode::InCell => match_token!(token {
                 tag @ </td> </th> => {
                     if self.in_scope_named(table_scope, tag.name.clone()) {
-                        self.generate_implied_end(cursory_implied_end);
+                        self.generate_implied_end_tags(cursory_implied_end);
                         self.expect_to_close(tag.name);
                         self.clear_active_formatting_to_marker();
                         self.mode.set(InsertionMode::InRow);

rcdom/Cargo.toml

@@ -23,6 +23,7 @@ xml5ever = { version = "0.22", path = "../xml5ever" }
 [dev-dependencies]
 libtest-mimic = "0.8.1"
 serde_json = "1.0"
+env_logger = "0.10"
 
 [[test]]
 name = "html-tokenizer"

rcdom/examples/hello_xml.rs

@@ -17,6 +17,8 @@ use xml5ever::tendril::TendrilSink;
 use xml5ever::tree_builder::TreeSink;
 
 fn main() {
+    env_logger::init();
+
     // To parse a string into a tree of nodes, we need to invoke
     // `parse_document` and supply it with a TreeSink implementation (RcDom).
     let dom: RcDom = parse_document(RcDom::default(), Default::default()).one("<hello>XML</hello>");

rcdom/examples/html2html.rs

@@ -27,6 +27,8 @@ use html5ever::{parse_document, serialize};
 use rcdom::{RcDom, SerializableHandle};
 
 fn main() {
+    env_logger::init();
+
     let opts = ParseOpts {
         tree_builder: TreeBuilderOpts {
             drop_doctype: true,

rcdom/examples/xml_tree_printer.rs

@@ -51,6 +51,8 @@ fn walk(prefix: &str, handle: &Handle) {
 }
 
 fn main() {
+    env_logger::init();
+
     let stdin = io::stdin();
 
     // To parse XML into a tree form, we need a TreeSink

rcdom/tests/html-tokenizer.rs

@@ -92,7 +92,7 @@ impl TokenLogger {
     }
 
     fn finish_str(&self) {
-        if self.current_str.borrow().len() > 0 {
+        if !self.current_str.borrow().is_empty() {
             let s = self.current_str.take();
             self.tokens.borrow_mut().push(CharacterTokens(s));
         }

rcdom/tests/html-tree-builder.rs

@@ -76,7 +76,7 @@ fn parse_tests<It: Iterator<Item = String>>(mut lines: It) -> Vec<HashMap<String
 
 fn serialize(buf: &mut String, indent: usize, handle: Handle) {
     buf.push('|');
-    buf.extend(iter::repeat(" ").take(indent));
+    buf.extend(iter::repeat_n(" ", indent));
 
     let node = handle;
     match node.data {
@@ -127,7 +127,7 @@ fn serialize(buf: &mut String, indent: usize, handle: Handle) {
 
             for attr in attrs.into_iter() {
                 buf.push('|');
-                buf.extend(iter::repeat(" ").take(indent + 2));
+                buf.extend(iter::repeat_n(" ", indent + 2));
                 match attr.name.ns {
                     ns!(xlink) => buf.push_str("xlink "),
                     ns!(xml) => buf.push_str("xml "),
@@ -152,7 +152,7 @@ fn serialize(buf: &mut String, indent: usize, handle: Handle) {
     {
         if let Some(ref content) = &*template_contents.borrow() {
             buf.push('|');
-            buf.extend(iter::repeat(" ").take(indent + 2));
+            buf.extend(iter::repeat_n(" ", indent + 2));
             buf.push_str("content\n");
             for child in content.children.borrow().iter() {
                 serialize(buf, indent + 4, child.clone());