From d94b344342d055434868dca8860fc0a9d1bbdbfb Mon Sep 17 00:00:00 2001
From: Darren Schroeder <343840+fdncred@users.noreply.github.com>
Date: Tue, 17 Dec 2024 06:26:56 -0600
Subject: [PATCH] =?UTF-8?q?Revert=20"For=20`#`=20to=20start=20a=20comment,?=
 =?UTF-8?q?=20then=20it=20either=20need=20to=20be=20the=20first=20chara?=
 =?UTF-8?q?=E2=80=A6"=20(#14606)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reverts nushell/nushell#14562 due to https://github.com/nushell/nushell/issues/14605
---
 crates/nu-parser/src/lex.rs        | 12 ++++-----
 crates/nu-parser/tests/test_lex.rs | 23 -----------------
 tests/repl/test_parser.rs          | 40 ------------------------------
 3 files changed, 6 insertions(+), 69 deletions(-)

diff --git a/crates/nu-parser/src/lex.rs b/crates/nu-parser/src/lex.rs
index 6d1adf28ef..f0802fcd7a 100644
--- a/crates/nu-parser/src/lex.rs
+++ b/crates/nu-parser/src/lex.rs
@@ -51,7 +51,7 @@ impl BlockKind {
 }
 
 // A baseline token is terminated if it's not nested inside of a paired
-// delimiter and the next character is one of: `|`, `;` or any
+// delimiter and the next character is one of: `|`, `;`, `#` or any
 // whitespace.
 fn is_item_terminator(
     block_level: &[BlockKind],
@@ -115,7 +115,6 @@ pub fn lex_item(
     //   character (whitespace, `|`, `;` or `#`) is encountered, the baseline
     //   token is done.
     // - Otherwise, accumulate the character into the current baseline token.
-    let mut previous_char = None;
     while let Some(c) = input.get(*curr_offset) {
         let c = *c;
 
@@ -148,9 +147,11 @@ pub fn lex_item(
                 // Also need to check to make sure we aren't escaped
                 quote_start = None;
             }
-        } else if c == b'#' && !in_comment {
-            // To start a comment, It either need to be the first character of the token or prefixed with space.
-            in_comment = previous_char.map(|pc| pc == b' ').unwrap_or(true);
+        } else if c == b'#' {
+            if is_item_terminator(&block_level, c, additional_whitespace, special_tokens) {
+                break;
+            }
+            in_comment = true;
         } else if c == b'\n' || c == b'\r' {
             in_comment = false;
             if is_item_terminator(&block_level, c, additional_whitespace, special_tokens) {
@@ -253,7 +254,6 @@ pub fn lex_item(
         }
 
         *curr_offset += 1;
-        previous_char = Some(c);
     }
 
     let span = Span::new(span_offset + token_start, span_offset + *curr_offset);
diff --git a/crates/nu-parser/tests/test_lex.rs b/crates/nu-parser/tests/test_lex.rs
index 54ff674bb9..a14843f3f0 100644
--- a/crates/nu-parser/tests/test_lex.rs
+++ b/crates/nu-parser/tests/test_lex.rs
@@ -159,29 +159,6 @@ fn lex_comment() {
     );
 }
 
-#[test]
-fn lex_not_comment_needs_space_in_front_of_hashtag() {
-    let file = b"1..10 | each {echo test#testing }";
-
-    let output = lex(file, 0, &[], &[], false);
-
-    assert!(output.1.is_none());
-}
-
-#[test]
-fn lex_comment_with_space_in_front_of_hashtag() {
-    let file = b"1..10 | each {echo test #testing }";
-
-    let output = lex(file, 0, &[], &[], false);
-
-    assert!(output.1.is_some());
-    assert!(matches!(
-        output.1.unwrap(),
-        ParseError::UnexpectedEof(missing_token, span) if missing_token == "}"
-            && span == Span::new(33, 34)
-    ));
-}
-
 #[test]
 fn lex_is_incomplete() {
     let file = b"let x = 300 | ;";
diff --git a/tests/repl/test_parser.rs b/tests/repl/test_parser.rs
index ddc790324a..f77d431110 100644
--- a/tests/repl/test_parser.rs
+++ b/tests/repl/test_parser.rs
@@ -169,41 +169,6 @@ fn comment_skipping_in_pipeline_3() -> TestResult {
     )
 }
 
-#[test]
-fn still_string_if_hashtag_is_middle_of_string() -> TestResult {
-    run_test(r#"echo test#testing"#, "test#testing")
-}
-
-#[test]
-fn non_comment_hashtag_in_comment_does_not_stop_comment() -> TestResult {
-    run_test(r#"# command_bar_text: { fg: '#C4C9C6' },"#, "")
-}
-
-#[test]
-fn non_comment_hashtag_in_comment_does_not_stop_comment_in_block() -> TestResult {
-    run_test(
-        r#"{
-        explore: {
-            # command_bar_text: { fg: '#C4C9C6' },
-        }
-    } | get explore | is-empty"#,
-        "true",
-    )
-}
-
-#[test]
-fn still_string_if_hashtag_is_middle_of_string_inside_each() -> TestResult {
-    run_test(
-        r#"1..1 | each {echo test#testing } | get 0"#,
-        "test#testing",
-    )
-}
-
-#[test]
-fn still_string_if_hashtag_is_middle_of_string_inside_each_also_with_dot() -> TestResult {
-    run_test(r#"1..1 | each {echo '.#testing' } | get 0"#, ".#testing")
-}
-
 #[test]
 fn bad_var_name() -> TestResult {
     fail_test(r#"let $"foo bar" = 4"#, "can't contain")
@@ -317,11 +282,6 @@ fn raw_string_with_equals() -> TestResult {
     )
 }
 
-#[test]
-fn raw_string_with_hashtag() -> TestResult {
-    run_test(r#"r##' one # two '##"#, "one # two")
-}
-
 #[test]
 fn list_quotes_with_equals() -> TestResult {
     run_test(