From 93c1f481abb43c33c53fca703a83a19d208b68df Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Kai=20K=C3=B6hne?= <kai.koehne@qt.io>
Date: Wed, 5 Jan 2022 08:29:21 +0100
Subject: Add QTextDocumentFragment::toRawText()

Like QTextDocument::toRawText(), QTextDocumentFragment::toRawText()
does allow access to the raw string without normalizing nbsp,
line separator, paragraph separator unicode characters.

[ChangeLog][QtGui][Text] Added QTextDocumentFragment::toRawText() function.

Task-number: QTBUG-99572
Change-Id: Ia74150a3870ea0e6326fdcda4d9d0410019124ae
Reviewed-by: Eskil Abrahamsen Blomfeldt <eskil.abrahamsen-blomfeldt@qt.io>
---
 src/gui/text/qtextdocumentfragment.cpp | 32 ++++++++++++++++++++++++++------
 src/gui/text/qtextdocumentfragment.h   |  1 +
 2 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'src/gui')

diff --git a/src/gui/text/qtextdocumentfragment.cpp b/src/gui/text/qtextdocumentfragment.cpp
index 24f2198d4e..f263e96154 100644
--- a/src/gui/text/qtextdocumentfragment.cpp
+++ b/src/gui/text/qtextdocumentfragment.cpp
@@ -266,12 +266,11 @@ void QTextDocumentFragmentPrivate::insert(QTextCursor &_cursor) const
     document fragment. Document fragments can also be created by the
     static functions, fromPlainText() and fromHtml().
 
-    The contents of a document fragment can be obtained as plain text
-    by using the toPlainText() function, or it can be obtained as HTML
+    The contents of a document fragment can be obtained as raw text
+    by using the toRawText() function, or it can be obtained as HTML
     with toHtml().
 */
 
-
 /*!
     Constructs an empty QTextDocumentFragment.
 
@@ -358,10 +357,16 @@ bool QTextDocumentFragment::isEmpty() const
 }
 
 /*!
-    Returns the document fragment's text as plain text (i.e. with no
-    formatting information).
+    This function returns the same as toRawText(), but will replace
+    some unicode characters with ASCII alternatives.
+    In particular, no-break space (U+00A0) is replaced by a regular
+    space (U+0020), and both paragraph (U+2029) and line (U+2028)
+    separators are replaced by line feed (U+000A).
+    If you need the precise contents of the document, use toRawText()
+    instead.
 
-    \sa toHtml()
+
+    \sa toHtml(), toRawText()
 */
 QString QTextDocumentFragment::toPlainText() const
 {
@@ -371,6 +376,21 @@ QString QTextDocumentFragment::toPlainText() const
     return d->doc->toPlainText();
 }
 
+/*!
+    Returns the document fragment's text as raw text (i.e. with no
+    formatting information).
+
+    \since 6.4
+    \sa toHtml(), toPlainText()
+*/
+QString QTextDocumentFragment::toRawText() const
+{
+    if (!d)
+        return QString();
+
+    return d->doc->toRawText();
+}
+
 #ifndef QT_NO_TEXTHTMLPARSER
 
 /*!
diff --git a/src/gui/text/qtextdocumentfragment.h b/src/gui/text/qtextdocumentfragment.h
index 2283b06c6c..37d7006ae6 100644
--- a/src/gui/text/qtextdocumentfragment.h
+++ b/src/gui/text/qtextdocumentfragment.h
@@ -64,6 +64,7 @@ public:
     bool isEmpty() const;
 
     QString toPlainText() const;
+    QString toRawText() const;
 #ifndef QT_NO_TEXTHTMLPARSER
     QString toHtml() const;
 #endif // QT_NO_TEXTHTMLPARSER
-- 
cgit v1.2.3