From 0f370ea91d78c7a0394417edbd9b0ea80ffed1c9 Mon Sep 17 00:00:00 2001
From: SavagePeanut <sourcehut@lazytapir.com>
Date: Tue, 15 Aug 2023 00:16:12 -0500
Subject: fix quoted code blocks

---
 src/lib.rs                 | 30 ++++++++++++++++++++----------
 tests/test_style_parser.py | 28 ++++++++++++++++++++++++----
 2 files changed, 44 insertions(+), 14 deletions(-)

diff --git a/src/lib.rs b/src/lib.rs
index 88b040d..ceca3a1 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -86,13 +86,14 @@ fn parse_with_limits(chars: &Vec<char>, start: usize, end: usize, depth: usize)
             }
             match seek_end_block(chars, c, end_of_line, end, depth) {
                 Some(to) => {
+                    println!("to {}", to);
                     if to != index + 3 && is_quote_start(chars, index, depth) {
                         let keyword = if end_of_line == index + 3 {
                             "```".to_string()
                         } else {
                             "```language".to_string()
                         };
-                        let remove_end = if depth > 0 && to == end {
+                        let remove_end = if depth > 0 && (to == end || to == chars.len()) {
                             to
                         } else {
                             to + 4 + depth
@@ -242,7 +243,6 @@ fn seek_higher_order_end(chars: &Vec<char>, keyword: char, start: usize, repetit
         if c == keyword
             && chars[i - 1].is_whitespace()
             && !followed_by_whitespace(chars, i, end)
-            && !preceeded_by_backslash(chars, i, start)
             && is_char_repeating(chars, keyword, repetitions, i + 1, end)
         {
             return None; // "*bold* *<--- beginning of new bold>*"
@@ -283,17 +283,27 @@ fn seek_end_of_quote(chars: &Vec<char>, start: usize, end: usize, depth: usize)
 
 fn seek_end_block(chars: &Vec<char>, keyword: char, start: usize, end: usize, depth: usize) -> Option<usize> {
     for i in start..=end {
-        if chars[i] == '\n'
-            && i + 4 + depth > end
-            && (depth == 0 || chars[i + 1..i + 1 + depth].iter().all(|&c| QUOTE_KEYWORDS.contains(&c)))
-            && chars[i + 1 + depth] == keyword
-            && is_char_repeating(chars, keyword, 2, i + 1 + depth, end)
-        {
-            return Some(i);
+        if chars[i] == '\n' {
+            if i + depth == end && chars[i + 1..i + 1 + depth].iter().all(|&c| QUOTE_KEYWORDS.contains(&c)) {
+                continue;
+            }
+            if i + 1 + depth > end {
+                return Some(i);
+            }
+            if i + 4 + depth > end
+                && chars[i + 1..i + 1 + depth].iter().all(|&c| QUOTE_KEYWORDS.contains(&c))
+                && chars[i + 1 + depth] == keyword
+                && is_char_repeating(chars, keyword, 2, i + 1 + depth, end)
+            {
+                return Some(i);
+            }
         }
     }
     if end == chars.len() - 1 {
-        return None;
+        if depth == 0 {
+            return None;
+        }
+        return Some(chars.len());
     }
     Some(end)
 }
diff --git a/tests/test_style_parser.py b/tests/test_style_parser.py
index d873644..673b63c 100644
--- a/tests/test_style_parser.py
+++ b/tests/test_style_parser.py
@@ -98,14 +98,14 @@ def test_code_blocks():
     formatted_body = "<blockquote><pre><code class=\"language-java\">why are you quoting a code block</code></pre></blockquote>"
     assert(format_body(test, MATRIX_FORMATS) == formatted_body)
 
-    test = ">```\n>please stop trying to break my parser ;-;\n>```"
-    formatted_body = "<blockquote><pre><code>please stop trying to break my parser ;-;</code></pre></blockquote>"
-    assert(format_body(test, MATRIX_FORMATS) == formatted_body)
-
     test = ">>```\n>>double quote code block\n>single quote not in code block\nnormal text"
     formatted_body = "<blockquote><blockquote><pre><code>double quote code block</code></pre></blockquote>\nsingle quote not in code block</blockquote>\nnormal text"
     assert(format_body(test, MATRIX_FORMATS) == formatted_body)
 
+    test = ">```\n>please stop trying to break my parser ;-;"
+    formatted_body = "<blockquote><pre><code>please stop trying to break my parser ;-;</code></pre></blockquote>"
+    assert(format_body(test, MATRIX_FORMATS) == formatted_body)
+
     test = ">>```\n>>>>double quote code block\n>single quote not in code block\nnormal text"
     formatted_body = "<blockquote><blockquote><pre><code>>>double quote code block</code></pre></blockquote>\nsingle quote not in code block</blockquote>\nnormal text"
     assert(format_body(test, MATRIX_FORMATS) == formatted_body)
@@ -203,6 +203,10 @@ def test_no_changes():
     assert(format_body(test, MATRIX_FORMATS) == formatted_body)
 
 def test_assorted():
+    test = "\n"
+    formatted_body = "\n"
+    assert(format_body(test, MATRIX_FORMATS) == formatted_body)
+
     test = "at the ||end||"
     formatted_body = "at the <span data-mx-spoiler>end</span>"
     assert(format_body(test, MATRIX_FORMATS) == formatted_body)
@@ -215,6 +219,22 @@ def test_assorted():
     formatted_body = "<em>underline</em> <strong>bold</strong> <strike>strikethrough</strike> >not quote <span data-mx-spoiler>spoiler</span>\n<blockquote>quote</blockquote>\nnothing\nnothing\n<blockquote><blockquote><blockquote><blockquote>another quote with <span data-mx-spoiler><strike><em><strong>```four```</strong></em></strike></span></blockquote></blockquote></blockquote></blockquote>"
     assert(format_body(test, MATRIX_FORMATS) == formatted_body)
 
+    test = ">```\n>do be do be dooo ba do be do be do ba\n>>>"
+    formatted_body = "<blockquote><pre><code>do be do be dooo ba do be do be do ba\n>></code></pre></blockquote>"
+    assert(format_body(test, MATRIX_FORMATS) == formatted_body)
+
+    test = "\n\n>```\n>do be do be dooo ba do be do be do ba\na\n\n\naoeu\n"
+    formatted_body = "\n\n<blockquote><pre><code>do be do be dooo ba do be do be do ba</code></pre></blockquote>\na\n\n\naoeu\n"
+    assert(format_body(test, MATRIX_FORMATS) == formatted_body)
+
+    test = ">```\n>do be do be dooo ba do be do be do ba\n>\n>\n>aoeu"
+    formatted_body = "<blockquote><pre><code>do be do be dooo ba do be do be do ba\n\n\naoeu</code></pre></blockquote>"
+    assert(format_body(test, MATRIX_FORMATS) == formatted_body)
+
+    test = ">```\n>code block\n>```invalid\n"
+    formatted_body = "<blockquote><pre><code>code block\n```invalid</code></pre></blockquote>\n"
+    assert(format_body(test, MATRIX_FORMATS) == formatted_body)
+
 def test_weird_utf8():
     test = "❤️💓💕💖💗 ||💙💚💛💜🖤|| 💝💞💟❣️"
     formatted_body = "❤️💓💕💖💗 <span data-mx-spoiler>💙💚💛💜🖤</span> 💝💞💟❣️"
-- 
cgit v1.2.3