From 52fe1f7e4df3c801a0292b9ae78da1bb664c3e2e Mon Sep 17 00:00:00 2001
From: Cyprien de Saint Guilhem <cyprien.desaintguilhem@3milabs.tech>
Date: Mon, 14 Oct 2024 22:19:16 +0200
Subject: [PATCH] Document added regex

---
 src/regexes.rs | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/src/regexes.rs b/src/regexes.rs
index b698b16..53b1905 100644
--- a/src/regexes.rs
+++ b/src/regexes.rs
@@ -51,7 +51,17 @@ lazy_static! {
         Regex::new(r"(?P<prev>\S.*?)(?P<env>\\end\{)").unwrap();
     pub static ref RE_ITEM_SHARED_LINE: Regex =
         Regex::new(r"(?P<prev>\S.*?)(?P<env>\\item)").unwrap();
-    pub static ref RE_ENV_ITEM_SHARED_LINE: Regex =
-        Regex::new(r"(?P<prev>\S.*?)(?P<env>(\\begin\{|\\end\{|\\item ).*)")
-            .unwrap();
+    // Regex that matches any splitting command with non-whitespace characters before it and catches the previous text
+    // in a group called "prev" and captures the command itself and the remaining text in a group called "env".
+    pub static ref RE_ENV_ITEM_SHARED_LINE: Regex = Regex::new(
+        r"(?x)              # Enable extended mode
+        (?P<prev>\S.*?)     # <prev>: captures any number of characters starting with a non-whitespace
+                            # character until the start of the next group;
+        (?P<env>(           # <env>: captures any LaTeX command before which the line should be split
+            \\begin\{       # start of environments
+            |\\end\{        # end of environments
+            |\\item )       # list items (note the space before the closing bracket)
+        .*)"                // and any characters that follow the command
+    )
+    .unwrap();
 }