.vscode/settings.json

@@ -1,11 +1,5 @@
 {
     "rust-analyzer.linkedProjects": [
         "./demo/Cargo.toml"
-    ],
+    ]
-    "files.exclude": {
-        "**/*.rpyc": true,
-        "**/*.rpa": true,
-        "**/*.rpymc": true,
-        "**/cache/": true
-    }
 }

demo/demo.csv

@@ -0,0 +1,5 @@
+65279,1179403647,1463895090
+3.1415927,2.7182817,1.618034
+-40,-273.15
+13,42
+65537

demo/demo.rpy

@@ -1,9 +0,0 @@
-show black amogus # this is a comment
-# this is a full line comment
-what the heck
-"this is a string with a # comment"
-"this is a string over
-multiple lines"
-this is cool # comment
-
-huh

demo/src/main.rs

@@ -1,5 +1,5 @@
 use renrs;
 
 fn main() {
-    renrs::parse("demo.rpy");
+    renrs::parse("demo.csv");
 }

src/csv.pest

@@ -0,0 +1,9 @@
+// + indicates one or more times
+field = { (ASCII_DIGIT | "." | "-")+ }
+// ~ indicates directly followed by
+// * indicates zero or more times (optional)
+record = { field ~ ("," ~ field)* }
+// SOI - start of input
+// END - end of input
+// There may be trailing newlines at the end
+file = { SOI ~ (record ~ ("\r\n" | "\n"))* ~ "\n"* ~ EOI }

src/lib.rs

@@ -4,32 +4,32 @@ use pest::Parser;
 use pest_derive::Parser;
 
 #[derive(Parser)]
-#[grammar = "rpy.pest"]
+#[grammar = "csv.pest"]
-struct RpyParser;
+struct CSVParser;
 
 pub fn parse(file_path: &str) {
     let unparsed_file = fs::read_to_string(file_path).expect("cannot find file");
-    let file = RpyParser::parse(Rule::file, &unparsed_file)
+    let file = CSVParser::parse(Rule::file, &unparsed_file)
         .expect("unsuccessful parse") // unwrap the parse result
         .next().unwrap(); // get and unwrap the `file` rule; never fails
-    for line in file.into_inner() {
+
-        match line.as_rule() {
+    let mut field_sum = 0.0;
-            Rule::line => {
+    let mut record_count: u64 = 0;
-                println!("Line:");
+
-                for token in line.into_inner() {
+    for record in file.into_inner() {
-                    match token.as_rule() {
+        match record.as_rule() {
-                        Rule::token => {
+            Rule::record => {
-                            println!("{}", token.as_str());
+                record_count += 1;
-                        },
+
-                        _ => {
+                for field in record.into_inner() {
-                            println!("{}", token.as_str());
+                    field_sum += field.as_str().parse::<f64>().unwrap();
-                        }
-                    }
                 }
-                println!()
             },
             Rule::EOI => (),
             _ => unreachable!(),
         }
     }
+
+    println!("Sum of fields: {field_sum}");
+    println!("Number of records: {record_count}");
 }

src/rpy.pest

@@ -1,28 +0,0 @@
-// underscores mark are silent rules, are ignored
-WHITESPACE = _{ " " }
-
-// characters are anything but newlines
-char = { !NEWLINE ~ ANY }
-
-// token definition
-// http://pest.rs/book/grammars/syntax.html#atomic
-inner = @{ char* }
-
-token = { string | keyword }
-
-// has to be atomic for no implicit separate (spaces)
-keyword = @{ (!(WHITESPACE | NEWLINE) ~ ANY)+ }
-
-// strings cannot contain quotes
-// TODO: escaped quotes
-string_data = @{ (!"\"" ~ ANY)* }
-string = ${ "\"" ~ string_data ~ "\"" }
-
-// comments are a # followed by
-// any number of non-newline characters
-COMMENT = _{ "#" ~ char* }
-
-// lines are comprised of a statement
-line = { token+ }
-
-file = { SOI ~ line ~ (NEWLINE+ ~ line)* ~ NEWLINE* ~ EOI }