Auto merge of #78429 - casey:doctest-attribute-splitting, r=jyn514

[librustdoc] Only split lang string on `,`, ` `, and `\t`

Split markdown lang strings into tokens on `,`.

The previous behavior was to split lang strings into tokens on any
character that wasn't a `_`, `_`, or alphanumeric.

This is a potentially breaking change, so please scrutinize! See discussion in #78344.

I noticed some test cases that made me wonder if there might have been some reason for the original behavior:

```
t("{.no_run .example}", false, true, Ignore::None, true, false, false, false, v(), None);
t("{.sh .should_panic}", true, false, Ignore::None, false, false, false, false, v(), None);
t("{.example .rust}", false, false, Ignore::None, true, false, false, false, v(), None);
t("{.test_harness .rust}", false, false, Ignore::None, true, true, false, false, v(), None);
```

It seemed pretty peculiar to specifically test lang strings in braces, with all the tokens prefixed by `.`.

I did some digging, and it looks like the test cases were added way back in [this commit from 2014](3fef7a74ca) by `@skade.`

It looks like they were added just to make sure that the splitting was permissive, and aren't testing that those strings in particular are accepted.

Closes https://github.com/rust-lang/rust/issues/78344.

src/librustdoc/html/markdown.rs

@@ -780,6 +780,31 @@ impl LangString {
         Self::parse(string, allow_error_code_check, enable_per_target_ignores, None)
     }
 
+    fn tokens(string: &str) -> impl Iterator<Item = &str> {
+        // Pandoc, which Rust once used for generating documentation,
+        // expects lang strings to be surrounded by `{}` and for each token
+        // to be proceeded by a `.`. Since some of these lang strings are still
+        // loose in the wild, we strip a pair of surrounding `{}` from the lang
+        // string and a leading `.` from each token.
+
+        let string = string.trim();
+
+        let first = string.chars().next();
+        let last = string.chars().last();
+
+        let string = if first == Some('{') && last == Some('}') {
+            &string[1..string.len() - 1]
+        } else {
+            string
+        };
+
+        string
+            .split(|c| c == ',' || c == ' ' || c == '\t')
+            .map(str::trim)
+            .map(|token| if token.chars().next() == Some('.') { &token[1..] } else { token })
+            .filter(|token| !token.is_empty())
+    }
+
     fn parse(
         string: &str,
         allow_error_code_check: ErrorCodes,
@@ -793,11 +818,11 @@ impl LangString {
         let mut ignores = vec![];
 
         data.original = string.to_owned();
-        let tokens = string.split(|c: char| !(c == '_' || c == '-' || c.is_alphanumeric()));
+
+        let tokens = Self::tokens(string).collect::<Vec<&str>>();
 
         for token in tokens {
-            match token.trim() {
-                "" => {}
+            match token {
                 "should_panic" => {
                     data.should_panic = true;
                     seen_rust_tags = !seen_other_tags;
@@ -894,6 +919,7 @@ impl LangString {
                 _ => seen_other_tags = true,
             }
         }
+
         // ignore-foo overrides ignore
         if !ignores.is_empty() {
             data.ignore = Ignore::Some(ignores);

src/librustdoc/html/markdown/tests.rs

@@ -58,6 +58,9 @@ fn test_lang_string_parse() {
 
     t(Default::default());
     t(LangString { original: "rust".into(), ..Default::default() });
+    t(LangString { original: ".rust".into(), ..Default::default() });
+    t(LangString { original: "{rust}".into(), ..Default::default() });
+    t(LangString { original: "{.rust}".into(), ..Default::default() });
     t(LangString { original: "sh".into(), rust: false, ..Default::default() });
     t(LangString { original: "ignore".into(), ignore: Ignore::All, ..Default::default() });
     t(LangString {
@@ -75,16 +78,16 @@ fn test_lang_string_parse() {
         ..Default::default()
     });
     t(LangString { original: "allow_fail".into(), allow_fail: true, ..Default::default() });
-    t(LangString { original: "{.no_run .example}".into(), no_run: true, ..Default::default() });
+    t(LangString { original: "no_run,example".into(), no_run: true, ..Default::default() });
     t(LangString {
-        original: "{.sh .should_panic}".into(),
+        original: "sh,should_panic".into(),
         should_panic: true,
         rust: false,
         ..Default::default()
     });
-    t(LangString { original: "{.example .rust}".into(), ..Default::default() });
+    t(LangString { original: "example,rust".into(), ..Default::default() });
     t(LangString {
-        original: "{.test_harness .rust}".into(),
+        original: "test_harness,.rust".into(),
         test_harness: true,
         ..Default::default()
     });
@@ -100,6 +103,18 @@ fn test_lang_string_parse() {
         rust: false,
         ..Default::default()
     });
+    t(LangString {
+        original: "text,no_run, ".into(),
+        no_run: true,
+        rust: false,
+        ..Default::default()
+    });
+    t(LangString {
+        original: "text,no_run,".into(),
+        no_run: true,
+        rust: false,
+        ..Default::default()
+    });
     t(LangString {
         original: "edition2015".into(),
         edition: Some(Edition::Edition2015),
@@ -112,6 +127,29 @@ fn test_lang_string_parse() {
     });
 }
 
+#[test]
+fn test_lang_string_tokenizer() {
+    fn case(lang_string: &str, want: &[&str]) {
+        let have = LangString::tokens(lang_string).collect::<Vec<&str>>();
+        assert_eq!(have, want, "Unexpected lang string split for `{}`", lang_string);
+    }
+
+    case("", &[]);
+    case("foo", &["foo"]);
+    case("foo,bar", &["foo", "bar"]);
+    case(".foo,.bar", &["foo", "bar"]);
+    case("{.foo,.bar}", &["foo", "bar"]);
+    case("  {.foo,.bar}  ", &["foo", "bar"]);
+    case("foo bar", &["foo", "bar"]);
+    case("foo\tbar", &["foo", "bar"]);
+    case("foo\t, bar", &["foo", "bar"]);
+    case(" foo , bar ", &["foo", "bar"]);
+    case(",,foo,,bar,,", &["foo", "bar"]);
+    case("foo=bar", &["foo=bar"]);
+    case("a-b-c", &["a-b-c"]);
+    case("a_b_c", &["a_b_c"]);
+}
+
 #[test]
 fn test_header() {
     fn t(input: &str, expect: &str) {