From 12d8f0b64d4118a8561c92f31205ced9d95f4384 Mon Sep 17 00:00:00 2001
From: Jonas Jenwald <jonas.jenwald@gmail.com>
Date: Fri, 14 Jan 2022 18:44:38 +0100
Subject: [PATCH] Re-factor the `stringToPDFString` helper function for UTF-16
strings
This patch changes the function to instead utilize the `TextDecoder` for both kinds of UTF-16 BOM strings.
---
src/shared/util.js | 47 +++++++++++++++++++---------------------------
1 file changed, 19 insertions(+), 28 deletions(-)
diff --git a/src/shared/util.js b/src/shared/util.js
index 9d023bfce..083d2bc28 100644
--- a/src/shared/util.js
+++ b/src/shared/util.js
@@ -955,38 +955,29 @@ const PDFStringTranslateTable = [
];
function stringToPDFString(str) {
- const length = str.length,
- strBuf = [];
- // UTF-16BE BOM
- if (str[0] === "\xFE" && str[1] === "\xFF") {
- for (let i = 2; i < length; i += 2) {
- strBuf.push(
- String.fromCharCode((str.charCodeAt(i) << 8) | str.charCodeAt(i + 1))
- );
+ if (str[0] >= "\xEF") {
+ let encoding;
+ if (str[0] === "\xFE" && str[1] === "\xFF") {
+ encoding = "utf-16be";
+ } else if (str[0] === "\xFF" && str[1] === "\xFE") {
+ encoding = "utf-16le";
+ } else if (str[0] === "\xEF" && str[1] === "\xBB" && str[2] === "\xBF") {
+ encoding = "utf-8";
}
- return strBuf.join("");
- }
- // UTF-16LE BOM
- if (str[0] === "\xFF" && str[1] === "\xFE") {
- for (let i = 2; i < length; i += 2) {
- strBuf.push(
- String.fromCharCode((str.charCodeAt(i + 1) << 8) | str.charCodeAt(i))
- );
- }
- return strBuf.join("");
- }
- // UTF-8 BOM
- if (str[0] === "\xEF" && str[1] === "\xBB" && str[2] === "\xBF") {
- try {
- const decoder = new TextDecoder("utf-8", { fatal: true });
- const buffer = stringToBytes(str);
- return decoder.decode(buffer);
- } catch (ex) {
- warn(`stringToPDFString: "${ex}".`);
+
+ if (encoding) {
+ try {
+ const decoder = new TextDecoder(encoding, { fatal: true });
+ const buffer = stringToBytes(str);
+ return decoder.decode(buffer);
+ } catch (ex) {
+ warn(`stringToPDFString: "${ex}".`);
+ }
}
}
// ISO Latin 1
- for (let i = 0; i < length; ++i) {
+ const strBuf = [];
+ for (let i = 0, ii = str.length; i < ii; i++) {
const code = PDFStringTranslateTable[str.charCodeAt(i)];
strBuf.push(code ? String.fromCharCode(code) : str.charAt(i));
}