Add new processing rule and improve comments.
This commit is contained in:
parent
033b124b90
commit
9e33f42d34
@ -3,25 +3,42 @@
|
||||
const html = await Astro.slots.render("default");
|
||||
|
||||
// rule:
|
||||
// 1. If a line belongs to the area where the line break should be kept.
|
||||
// 2. If a line ends with [a-zA-Z] add a space to the end of the line.
|
||||
// 3. If a line does not start in ASCII chars, join it to the previous line.
|
||||
// 1. If a line belongs to the area where the line break should be kept,
|
||||
// do not process this line.
|
||||
// 2. If a line ends with [a-zA-Z], add a space to the end of this line.
|
||||
// 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.
|
||||
// This is important in using one newline character to wrap Chinese.
|
||||
const arr = html.split("\n");
|
||||
let articleHTMLFinal = arr[0];
|
||||
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++) {
|
||||
// The first line of the HTML string is a table-of-content head recognized by
|
||||
// remark-toc so it can be ignored.
|
||||
if (arr[i].charAt(arr[i].length - 1).match(/[a-zA-Z]/) !== null) {
|
||||
arr[i] += " ";
|
||||
}
|
||||
// Check if the current line belongs to some block area.
|
||||
if (arr[i].match(/^(<pre|<code|<blockquote|<table)/) !== null) {
|
||||
remainIntactArea = true;
|
||||
} else {
|
||||
remainIntactArea = false;
|
||||
}
|
||||
// -------- add space
|
||||
// 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] += " ";
|
||||
}
|
||||
// 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] += " ";
|
||||
}
|
||||
// -------- combine lines
|
||||
if (
|
||||
// (
|
||||
// If the first character is not ascii character,
|
||||
@ -29,9 +46,9 @@ for (let i = 1; i < arr.length; i++) {
|
||||
// the final character of previous line is not ascii character.
|
||||
// ) AND
|
||||
// Current line should not belong to area that remains intact.
|
||||
(arr[i].charAt(0).match(/[ -~]/) === null ||
|
||||
arr[i - 1].charAt(arr[i - 1].length - 1).match(/[ -~]/) === null) &&
|
||||
!remainIntactArea
|
||||
(arr[i].charAt(0).match(/[ -~]/) === null
|
||||
|| arr[i - 1].charAt(arr[i - 1].length - 1).match(/[ -~]/) === null)
|
||||
&& !remainIntactArea
|
||||
) {
|
||||
articleHTMLFinal += arr[i];
|
||||
} else {
|
||||
|
Loading…
Reference in New Issue
Block a user