From 4783b223121d4f1133f0bb14dfd62833d7348a07 Mon Sep 17 00:00:00 2001
From: m-holger <m.holger@qpdf.org>
Date: Sat, 27 Jul 2024 18:06:12 +0100
Subject: [PATCH] In ContentNormalizer::handleToken refactor handling of space
 tokens

Avoid writing each space char individually.
---
 libqpdf/ContentNormalizer.cc | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/libqpdf/ContentNormalizer.cc b/libqpdf/ContentNormalizer.cc
index 2582e729..bca8ad66 100644
--- a/libqpdf/ContentNormalizer.cc
+++ b/libqpdf/ContentNormalizer.cc
@@ -25,18 +25,25 @@ ContentNormalizer::handleToken(QPDFTokenizer::Token const& token)
     case QPDFTokenizer::tt_space:
         {
             std::string const& value = token.getRawValue();
-            size_t len = value.length();
-            for (size_t i = 0; i < len; ++i) {
-                char ch = value.at(i);
-                if (ch == '\r') {
-                    if ((i + 1 < len) && (value.at(i + 1) == '\n')) {
-                        // ignore
-                    } else {
-                        write("\n");
-                    }
-                } else {
-                    write(&ch, 1);
+            auto size = value.size();
+            size_t pos = 0;
+            auto r_pos = value.find('\r');
+            while (r_pos != std::string::npos) {
+                if (pos != r_pos) {
+                    write(&value[pos], r_pos - pos);
                 }
+                if (++r_pos >= size) {
+                    write("\n");
+                    return;
+                }
+                if (value[r_pos] != '\n') {
+                    write("\n");
+                }
+                pos = r_pos;
+                r_pos = value.find('\r', pos);
+            }
+            if (pos < size) {
+                write(&value[pos], size - pos);
             }
         }
         return;