1 files changed, 33 insertions, 6 deletions

diff --git a/src/common-util/wiki-data.js b/src/common-util/wiki-data.js
index a4c6b3bd..546f1ad9 100644
--- a/src/common-util/wiki-data.js
+++ b/src/common-util/wiki-data.js
@@ -57,10 +57,9 @@ export function getKebabCase(name) {
 
 // Specific data utilities
 
-// Matches heading details from commentary data in roughly the formats:
+// Matches heading details from commentary data in roughly the format:
 //
-//    <i>artistReference:</i> (annotation, date)
-//    <i>artistReference|artistDisplayText:</i> (annotation, date)
+//    <i>artistText:</i> (annotation, date)
 //
 // where capturing group "annotation" can be any text at all, except that the
 // last entry (past a comma or the only content within parentheses), if parsed
@@ -83,8 +82,9 @@ export function getKebabCase(name) {
 // parentheses can be part of the actual annotation content.
 //
 // Capturing group "artistReference" is all the characters between <i> and </i>
-// (apart from the pipe and "artistDisplayText" text, if present), and is either
-// the name of an artist or an "artist:directory"-style reference.
+// (apart from the pipe and the "artistText" group, if present), and is either
+// the name of one or more artist or "artist:directory"-style references,
+// joined by commas, if multiple.
 //
 // This regular expression *doesn't* match bodies, which will need to be parsed
 // out of the original string based on the indices matched using this.
@@ -94,7 +94,7 @@ const dateRegex = groupName =>
   String.raw`(?<${groupName}>[a-zA-Z]+ [0-9]{1,2}, [0-9]{4,4}|[0-9]{1,2} [^,]*[0-9]{4,4}|[0-9]{1,4}[-/][0-9]{1,4}[-/][0-9]{1,4})`;
 
 const commentaryRegexRaw =
-  String.raw`^<i>(?<artistReferences>.+?)(?:\|(?<artistDisplayText>.+))?:<\/i>(?: \((?<annotation>(?:.*?(?=,|\)[^)]*$))*?)(?:,? ?(?:(?<dateKind>sometime|throughout|around) )?${dateRegex('date')}(?: ?- ?${dateRegex('secondDate')})?(?: (?<accessKind>captured|accessed) ${dateRegex('accessDate')})?)?\))?`;
+  String.raw`^<i>(?<artistText>.+?):<\/i>(?: \((?<annotation>(?:.*?(?=,|\)[^)]*$))*?)(?:,? ?(?:(?<dateKind>sometime|throughout|around) )?${dateRegex('date')}(?: ?- ?${dateRegex('secondDate')})?(?: (?<accessKind>captured|accessed) ${dateRegex('accessDate')})?)?\))?`;
 export const commentaryRegexCaseInsensitive =
   new RegExp(commentaryRegexRaw, 'gmi');
 export const commentaryRegexCaseSensitive =
@@ -522,3 +522,30 @@ export function combineWikiDataArrays(arrays) {
     return combined;
   }
 }
+
+// Markdown stuff
+
+export function* matchMarkdownLinks(markdownSource, {marked}) {
+  const plausibleLinkRegexp = /\[.*?\)/g;
+
+  let plausibleMatch = null;
+  while (plausibleMatch = plausibleLinkRegexp.exec(markdownSource)) {
+    // Pedantic rules use more particular parentheses detection in link
+    // destinations - they allow one level of balanced parentheses, and
+    // otherwise, parentheses must be escaped. This allows for entire links
+    // to be wrapped in parentheses, e.g below:
+    //
+    //   This is so cool. ([You know??](https://example.com))
+    //
+    const definiteMatch =
+      marked.Lexer.rules.inline.pedantic.link
+        .exec(markdownSource.slice(plausibleMatch.index));
+
+    if (definiteMatch) {
+      const [{length}, label, href] = definiteMatch;
+      const index = plausibleMatch.index + definiteMatch.index;
+
+      yield {label, href, index, length};
+    }
+  }
+}