From 5d4d388fe81b90afdfaa533b233c2d9e5d1a24a8 Mon Sep 17 00:00:00 2001
From: liding <ld.sino@outlook.com>
Date: Tue, 6 Aug 2024 11:00:42 +0800
Subject: [PATCH] Add new processing rule and improve comments.

---
 .../article/article_body/ArticleBody.astro    | 21 +++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/src/components/article/article_body/ArticleBody.astro b/src/components/article/article_body/ArticleBody.astro
index 392ecc5..93af240 100644
--- a/src/components/article/article_body/ArticleBody.astro
+++ b/src/components/article/article_body/ArticleBody.astro
@@ -9,6 +9,10 @@ const html = await Astro.slots.render("default");
 //   3. If a line ends without [a-zA-Z] and its next line starts with [a-zA-Z],
 //      add a heading space to the next line.
 //   4. If a line does not start in ASCII chars, join it to its previous line.
+//   5. If a line starts with <strong> or <em>, add a heading space to this
+//      line.
+//   6. If a line ends with </strong> or </em>, add a tailing space to this
+//      line.
 // This is important in using one newline character to wrap Chinese.
 const arr = html.split("\n");
 let articleHTMLFinal = arr[0];
@@ -16,6 +20,7 @@ let remainIntactArea = false;
 // The first line of the HTML string is a table-of-content head recognized by
 // remark-toc so it can be ignored.
 for (let i = 1; i < arr.length; i++) {
+  // rule 1
   // Check if the current line belongs to some block area.
   if (arr[i].match(/^(<pre|<code|<blockquote|<table)/) !== null) {
     remainIntactArea = true;
@@ -23,22 +28,34 @@ for (let i = 1; i < arr.length; i++) {
     remainIntactArea = false;
   }
   // -------- add space
+  // rule 2
   // If the last character of the current line is [a-zA-Z], add a space to the
   // end of the line.
   if (arr[i].charAt(arr[i].length - 1).match(/[a-zA-Z]/) !== null) {
     arr[i] += " ";
   }
+  // rule 3
   // The current is not the last line.
   // AND
   // The current line ends without [a-zA-Z].
   // AND
   // The next line starts with [a-zA-Z].
   if (i + 1 < arr.length
-      && arr[i].charAt(arr[i].length - 1).match(/[a-zA-Z]/) === null
-      && arr[i + 1].charAt(0).match(/[a-zA-Z]/) !== null) {
+    && arr[i].charAt(arr[i].length - 1).match(/[a-zA-Z]/) === null
+    && arr[i + 1].charAt(0).match(/[a-zA-Z]/) !== null
+  ) {
     arr[i] += " ";
   }
+  // rule 5
+  if (arr[i].match(/^(<em>|<strong>)/) !== null){
+    arr[i] = " " + arr[i];
+  }
+  // rule 6
+  if (arr[i].match(/(<\/em>|<\/strong>)$/) !== null){
+    arr[i] = arr[i] + " ";
+  }
   // -------- combine lines
+  // rule 4
   if (
     // (
     //   If the first character is not ascii character,