Merge pull request #192 from vojtechkral/code-num-backticks

Add the NodeCode struct to expose number of backticks from inline code spans
kivikakk · Jul 15, 2021 · 7b1f19f · 7b1f19f
2 parents 38beddb + 7284d7f
commit 7b1f19f
Show file tree

Hide file tree

Showing 7 changed files with 74 additions and 14 deletions.
diff --git a/examples/headers.rs b/examples/headers.rs
@@ -3,7 +3,7 @@
 extern crate comrak;
 
 use comrak::{
-    nodes::{AstNode, NodeValue},
+    nodes::{AstNode, NodeCode, NodeValue},
     parse_document, Arena, ComrakOptions,
 };
 
@@ -40,7 +40,7 @@ fn get_document_title(document: &str) -> String {
 
 fn collect_text<'a>(node: &'a AstNode<'a>, output: &mut Vec<u8>) {
     match node.data.borrow().value {
-        NodeValue::Text(ref literal) | NodeValue::Code(ref literal) => {
+        NodeValue::Text(ref literal) | NodeValue::Code(NodeCode { ref literal, .. }) => {
             output.extend_from_slice(literal)
         }
         NodeValue::LineBreak | NodeValue::SoftBreak => output.push(b' '),

diff --git a/examples/s-expr.rs b/examples/s-expr.rs
@@ -44,11 +44,19 @@ fn iter_nodes<'a, W: Write>(
     match &node.data.borrow().value {
         Text(t) => write!(writer, "{:?}", String::from_utf8_lossy(&t))?,
         value => {
-            try_node_inline!(value, Code);
             try_node_inline!(value, FootnoteDefinition);
             try_node_inline!(value, FootnoteReference);
             try_node_inline!(value, HtmlInline);
 
+            if let Code(code) = value {
+                return write!(
+                    writer,
+                    "Code({:?}, {})",
+                    String::from_utf8_lossy(&code.literal),
+                    code.num_backticks
+                );
+            }
+
             let has_blocks = node.children().any(|c| c.data.borrow().value.block());
 
             write!(writer, "({:?}", value)?;

diff --git a/src/cm.rs b/src/cm.rs
@@ -313,7 +313,7 @@ impl<'a, 'o> CommonMarkFormatter<'a, 'o> {
             NodeValue::Text(ref literal) => self.format_text(literal, allow_wrap, entering),
             NodeValue::LineBreak => self.format_line_break(entering),
             NodeValue::SoftBreak => self.format_soft_break(allow_wrap, entering),
-            NodeValue::Code(ref literal) => self.format_code(literal, allow_wrap, entering),
+            NodeValue::Code(ref code) => self.format_code(&code.literal, allow_wrap, entering),
             NodeValue::HtmlInline(ref literal) => self.format_html_inline(literal, entering),
             NodeValue::Strong => self.format_strong(),
             NodeValue::Emph => self.format_emph(node),

diff --git a/src/html.rs b/src/html.rs
@@ -1,5 +1,5 @@
 use ctype::isspace;
-use nodes::{AstNode, ListType, NodeValue, TableAlignment};
+use nodes::{AstNode, ListType, NodeCode, NodeValue, TableAlignment};
 use parser::ComrakOptions;
 use regex::Regex;
 use scanners;
@@ -338,7 +338,7 @@ impl<'o> HtmlFormatter<'o> {
                     if plain {
                         match node.data.borrow().value {
                             NodeValue::Text(ref literal)
-                            | NodeValue::Code(ref literal)
+                            | NodeValue::Code(NodeCode { ref literal, .. })
                             | NodeValue::HtmlInline(ref literal) => {
                                 self.escape(literal)?;
                             }
@@ -369,7 +369,7 @@ impl<'o> HtmlFormatter<'o> {
 
     fn collect_text<'a>(&self, node: &'a AstNode<'a>, output: &mut Vec<u8>) {
         match node.data.borrow().value {
-            NodeValue::Text(ref literal) | NodeValue::Code(ref literal) => {
+            NodeValue::Text(ref literal) | NodeValue::Code(NodeCode { ref literal, .. }) => {
                 output.extend_from_slice(literal)
             }
             NodeValue::LineBreak | NodeValue::SoftBreak => output.push(b' '),
@@ -563,7 +563,7 @@ impl<'o> HtmlFormatter<'o> {
                     }
                 }
             }
-            NodeValue::Code(ref literal) => {
+            NodeValue::Code(NodeCode { ref literal, .. }) => {
                 if entering {
                     self.output.write_all(b"<code>")?;
                     self.escape(literal)?;

diff --git a/src/nodes.rs b/src/nodes.rs
@@ -114,7 +114,7 @@ pub enum NodeValue {
     LineBreak,
 
     /// **Inline**.  A [code span](https://github.github.com/gfm/#code-spans).
-    Code(Vec<u8>),
+    Code(NodeCode),
 
     /// **Inline**.  [Raw HTML](https://github.github.com/gfm/#raw-html) contained inline.
     HtmlInline(Vec<u8>),
@@ -160,6 +160,19 @@ pub enum TableAlignment {
     Right,
 }
 
+/// An inline [code span](https://github.github.com/gfm/#code-spans).
+#[derive(Debug, Clone)]
+pub struct NodeCode {
+    /// The URL for the link destination or image source.
+    pub num_backticks: usize,
+
+    /// The content of the inline code span.
+    /// As the contents are not interpreted as Markdown at all,
+    /// they are contained within this structure,
+    /// rather than inserted into a child inline of any kind.
+    pub literal: Vec<u8>,
+}
+
 /// The details of a link's destination, or an image's source.
 #[derive(Debug, Clone)]
 pub struct NodeLink {

diff --git a/src/parser/inlines.rs b/src/parser/inlines.rs
@@ -1,7 +1,7 @@
 use arena_tree::Node;
 use ctype::{ispunct, isspace};
 use entity;
-use nodes::{Ast, AstNode, NodeLink, NodeValue};
+use nodes::{Ast, AstNode, NodeCode, NodeLink, NodeValue};
 use parser::{unwrap_into_2, unwrap_into_copy, AutolinkType, Callback, ComrakOptions, Reference};
 use scanners;
 use std::cell::{Cell, RefCell};
@@ -518,7 +518,11 @@ impl<'a, 'r, 'o, 'd, 'i, 'c, 'subj> Subject<'a, 'r, 'o, 'd, 'i, 'c, 'subj> {
             Some(endpos) => {
                 let buf = &self.input[startpos..endpos - openticks];
                 let buf = strings::normalize_code(buf);
-                make_inline(self.arena, NodeValue::Code(buf))
+                let code = NodeCode {
+                    num_backticks: openticks,
+                    literal: buf,
+                };
+                make_inline(self.arena, NodeValue::Code(code))
             }
         }
     }

diff --git a/src/tests.rs b/src/tests.rs
@@ -1,3 +1,4 @@
+use crate::nodes::{AstNode, NodeCode, NodeValue};
 use cm;
 use html;
 use propfuzz::prelude::*;
@@ -95,6 +96,18 @@ macro_rules! html_opts {
     };
 }
 
+fn asssert_node_eq<'a>(node: &'a AstNode<'a>, location: &[usize], expected: &NodeValue) {
+    let node = location
+        .iter()
+        .fold(node, |node, &n| node.children().nth(n).unwrap());
+
+    let data = node.data.borrow();
+    let actual = format!("{:?}", data.value);
+    let expected = format!("{:?}", expected);
+
+    compare_strs(&actual, &expected, "ast comparison");
+}
+
 #[test]
 fn basic() {
     html(
@@ -310,6 +323,27 @@ fn backticks() {
     );
 }
 
+#[test]
+fn backticks_num() {
+    let input = "Some `code1`. More ``` code2 ```.\n";
+
+    let arena = Arena::new();
+    let options = ComrakOptions::default();
+    let root = parse_document(&arena, input, &options);
+
+    let code1 = NodeValue::Code(NodeCode {
+        num_backticks: 1,
+        literal: b"code1".to_vec(),
+    });
+    asssert_node_eq(root, &[0, 1], &code1);
+
+    let code2 = NodeValue::Code(NodeCode {
+        num_backticks: 3,
+        literal: b"code2".to_vec(),
+    });
+    asssert_node_eq(root, &[0, 3], &code2);
+}
+
 #[test]
 fn backslashes() {
     html(
@@ -1065,9 +1099,9 @@ fn exercise_full_api() {
 
     let _: String = ::Anchorizer::new().anchorize("header".to_string());
 
-    let _: &::nodes::AstNode = ::parse_document(&arena, "document", &default_options);
+    let _: &AstNode = ::parse_document(&arena, "document", &default_options);
 
-    let _: &::nodes::AstNode = ::parse_document_with_broken_link_callback(
+    let _: &AstNode = ::parse_document_with_broken_link_callback(
         &arena,
         "document",
         &default_options,
@@ -1168,7 +1202,8 @@ fn exercise_full_api() {
         ::nodes::NodeValue::SoftBreak => {}
         ::nodes::NodeValue::LineBreak => {}
         ::nodes::NodeValue::Code(code) => {
-            let _: &Vec<u8> = code;
+            let _: usize = code.num_backticks;
+            let _: Vec<u8> = code.literal;
         }
         ::nodes::NodeValue::HtmlInline(html) => {
             let _: &Vec<u8> = html;