WIP: Parse tags starting with digits and containing spaces (close #1072)

common/markdown_parser/constants.ts

@@ -1,5 +1,5 @@
 export const wikiLinkRegex = /(!?\[\[)([^\]\|]+)(?:\|([^\]]+))?(\]\])/g; // [fullMatch, firstMark, url, alias, lastMark]
 export const mdLinkRegex = /!?\[(?<title>[^\]]*)\]\((?<url>.+)\)/g; // [fullMatch, alias, url]
 export const tagRegex =
-  /#[^\d\s!@#$%^&*(),.?":{}|<>\\][^\s!@#$%^&*(),.?":{}|<>\\]*/;
+  /#(?:(?:\d*[^\d\s!@#$%^&*(),.?":{}|<>\\][^\s!@#$%^&*(),.?":{}|<>\\]*)|(?:"[^"\n]+")|(?:<[^>\n]+>))/;
 export const pWikiLinkRegex = new RegExp("^" + wikiLinkRegex.source); // Modified regex used only in parser

common/markdown_parser/parser.test.ts

@@ -162,3 +162,40 @@ Deno.test("Test lua directive parser", () => {
   const simpleExample = `Simple \${{a=}}`;
   console.log(JSON.stringify(parseMarkdown(simpleExample), null, 2));
 });
+
+const hashtagSample = `
+Hashtags, e.g. #mytag but ignore in code \`#mytag\`.
+They can contain slashes like #level/beginner, single quotes, and dashes: #Mike's-idea.
+Can be just #a single letter.
+But no other #interpunction: #exclamation! #question?
+There are two ways to make #"tag with spaces and <angle>" #<tag with spaces and "quote">
+These cannot span #"multiple
+lines"
+#no#spacing also works.
+Hashtags can start with number if there's something after it: #3dprint #15-52_Trip-to-NYC.
+But magazine issue #123 is not a hashtag.
+Should support other languages, like #żółć or #井号
+`;
+
+Deno.test("Test hashtag parser", () => {
+  const tree = parseMarkdown(hashtagSample);
+  const hashtags = collectNodesOfType(tree, "Hashtag");
+  assertEquals(hashtags.length, 15);
+
+  assertEquals(hashtags[0].children![0].text, "#mytag");
+  assertEquals(hashtags[1].children![0].text, "#level/beginner");
+  assertEquals(hashtags[2].children![0].text, "#Mike's-idea");
+  assertEquals(hashtags[2].children![0].text, "#a");
+  assertEquals(hashtags[3].children![0].text, "#interpunction");
+  assertEquals(hashtags[4].children![0].text, "#exclamation");
+  assertEquals(hashtags[5].children![0].text, "#question");
+  assertEquals(hashtags[6].children![0].text, '#"tag with spaces and <angle>"');
+  assertEquals(hashtags[7].children![0].text, '#<tag with spaces and "quote">');
+  // multiple lines not allowed
+  assertEquals(hashtags[8].children![0].text, "#no");
+  assertEquals(hashtags[9].children![0].text, "#spacing");
+  assertEquals(hashtags[10].children![0].text, "#3dprint");
+  assertEquals(hashtags[11].children![0].text, "#15-52_Trip-to-NYC");
+  assertEquals(hashtags[12].children![0].text, "#żółć");
+  assertEquals(hashtags[13].children![0].text, "#井号");
+});

website/Markdown/Extensions.md

@@ -10,7 +10,7 @@ In addition to supporting [[Markdown/Basics|markdown basics]] as standardized by
 * [[Transclusions]] syntax
 * [[Markdown/Anchors]]
 * [[Markdown/Admonitions]]
-* Hashtags, e.g. `#mytag`.
+* [[Markdown/Hashtags]]
 * [[Markdown/Command links]] syntax
 * [Tables](https://www.markdownguide.org/extended-syntax/#tables)
 * [Task lists](https://www.markdownguide.org/extended-syntax/#task-lists)

website/Markdown/Hashtags.md

@@ -0,0 +1,16 @@
+#level/beginner
+
+These can be used in text to assign an [[Objects#tag]] #like-this. If hashtags are the only content of first paragraph, they are applied to the entire page.
+
+Hashtags can contain letters, dashes, underscores and other characters, but not:
+- Whitespace (space, newline etc.)
+- Characters from this list `!@#$%^&*(),.?":{}|<>\`
+- Consist of digits only #123 (but #3dprint is recognised)
+
+If you need your tags to contain these characters, you have to surround the tag content with either:
+- Double quotes `#"tag in quotes"` #“tag in quotes”
+- Angle brackets #<tag in angle> #<tag in angle>
+
+```query
+tag where page = @page.name
+```