Implement extended support for comments in bib source files (#80)

Author: jakewilliami

src/lib.rs

@@ -1053,6 +1053,33 @@ mod tests {
         dump_author_title("tests/polaritons.bib");
     }
 
+    #[test]
+    fn test_comments() {
+        let contents = fs::read_to_string("tests/comments.bib").unwrap();
+
+        let bibliography = Bibliography::parse(&contents).unwrap();
+
+        assert_eq!(
+            bibliography.keys().collect::<Vec<_>>(),
+            &[
+                "mcelreath2007mathematical",
+                "fischer2022equivalence",
+                "roes2003belief",
+                "wong2016null",
+            ]
+        );
+
+        assert_eq!(
+            bibliography
+                .get("wong2016null")
+                .unwrap()
+                .title()
+                .unwrap()
+                .format_verbatim(),
+            "Null hypothesis testing (I)-5% significance level"
+        );
+    }
+
     #[test]
     fn test_extended_name_format() {
         dump_author_title("tests/extended_name_format.bib");

src/raw.rs

@@ -167,8 +167,11 @@ impl<'s> BiblatexParser<'s> {
     pub fn parse(mut self) -> Result<RawBibliography<'s>, ParseError> {
         while !self.s.done() {
             self.s.eat_whitespace();
+
             match self.s.peek() {
                 Some('@') => self.entry()?,
+                // Handle comments outside of entry
+                Some('%') => self.comment()?,
                 Some(_) => {
                     self.s.eat();
                 }
@@ -360,7 +363,13 @@ impl<'s> BiblatexParser<'s> {
 
         let value = self.abbr_field()?;
 
+        // Handle inline comments before closing brace at end of entry:
+        //     @article{foo,
+        //         title={bar},
+        //         year={2025}  % A comment
+        //     }
         self.s.eat_whitespace();
+        self.comment()?;
 
         Ok((key, value))
     }
@@ -393,7 +402,17 @@ impl<'s> BiblatexParser<'s> {
             fields.push(Pair::new(key, value));
 
             match self.s.peek() {
-                Some(',') => self.comma()?,
+                Some(',') => {
+                    self.comma()?;
+
+                    // Handle inline comments after comma at end of field
+                    //     @article{foo,
+                    //         title={bar},  % A comment
+                    //         year={2025}
+                    //     }
+                    self.s.eat_whitespace();
+                    self.comment()?;
+                }
                 Some('}') => {
                     return Ok(fields);
                 }
@@ -486,6 +505,14 @@ impl<'s> BiblatexParser<'s> {
         self.s.eat_whitespace();
         self.comma()?;
 
+        // Handle inline comments after entry key
+        //     @article{foo,  % A comment
+        //         title={bar},
+        //         year={2025}
+        //     }
+        self.s.eat_whitespace();
+        self.comment()?;
+
         self.s.eat_whitespace();
         let fields = self.fields()?;
 
@@ -495,6 +522,14 @@ impl<'s> BiblatexParser<'s> {
         Ok(())
     }
 
+    /// Eat an inline comment.
+    fn comment(&mut self) -> Result<(), ParseError> {
+        if self.s.eat_if('%') {
+            self.s.eat_until('\n');
+        }
+        Ok(())
+    }
+
     fn here(&self) -> Span {
         self.s.cursor()..self.s.cursor()
     }

tests/comments.bib

@@ -0,0 +1,51 @@
+% Comments before the entry works
+@book{mcelreath2007mathematical,
+  title={Mathematical models of social evolution: A guide for the perplexed},
+  author={McElreath, Richard and Boyd, Robert},
+  year={2007},
+  publisher={University of Chicago Press},
+  address={Chicago}
+}
+
+@article{fischer2022equivalence,
+  title={Why equivalence and invariance are both different and essential for scientific studies of culture: A discussion of mapping processes and theoretical implications},
+  author={Fischer, Ronald and Karl, Johannes and Luczak-Roesch, Markus},
+  year={2022},  % An inline comment should also work
+  publisher={PsyArXiv},
+  % A comment on a new line of the entry
+  url={https://files.osf.io/v1/resources/fst9k/providers/osfstorage/6312eb42e7f1b7082aaae63c}
+}
+
+% Commented-out blocks should also work
+% @manual{rlang,
+%   title={R: A Language and Environment for Statistical Computing},
+%   author={{R Core Team}},
+%   organization={R Foundation for Statistical Computing},
+%   address={Vienna, Austria},
+%   year={2024},
+%   url={https://www.R-project.org/}
+% }
+
+@article{roes2003belief,  % A comment after the entry key
+  title={Belief in moralizing gods},
+  author={Roes, Frans L and Raymond, Michel},
+  journal={Evolution and human behavior},
+  volume={24},
+  number={2},
+  pages={126--135},
+  year={2003},
+  publisher={Elsevier},
+  doi={10.1016/S1090-5138(02)00134-4}
+}  % A comment after the entry
+
+% This is an example of a percent symbol in the content of the entry, so we must ignore after the % too eagerly
+@article{wong2016null,
+  title={Null hypothesis testing ({I})-5\% significance level},
+  author={Wong, Kai-Choi},
+  journal={East Asian Archives of Psychiatry},
+  volume={26},
+  number={3},
+  pages={112--113},
+  year={2016},
+  publisher={Hong Kong College of Psychiatrists}  % A comment at the end of the entry
+}