Move move prependUnicodeMarker to UTF.h

... and rename it to prependUnicodeByteOrderMark.

Now all unicode code has moved from GooString.h to UTF.h.

6 files changed, 16 insertions, 17 deletions

diff --git a/glib/poppler-document.cc b/glib/poppler-document.cc
index 5dc034c5..fac52af8 100644
--- a/glib/poppler-document.cc
+++ b/glib/poppler-document.cc
@@ -1140,7 +1140,7 @@ static GooString *_poppler_goo_string_from_utf8(const gchar *src)
     g_free(utf16);
 
     if (!hasUnicodeByteOrderMark(result->toStr())) {
-        result->prependUnicodeMarker();
+        prependUnicodeByteOrderMark(result->toNonConstStr());
     }
 
     return result;
diff --git a/goo/GooString.cc b/goo/GooString.cc
index ff845597..a657e82f 100644
--- a/goo/GooString.cc
+++ b/goo/GooString.cc
@@ -620,8 +620,3 @@ std::string GooString::toLowerCase(const std::string &s)
     lowerCase(newString);
     return s;
 }
-
-void GooString::prependUnicodeMarker()
-{
-    insert(0, "\xFE\xFF", 2);
-}
diff --git a/goo/GooString.h b/goo/GooString.h
index 05aa630f..5659b34b 100644
--- a/goo/GooString.h
+++ b/goo/GooString.h
@@ -242,8 +242,6 @@ public:
 
     // Return true if string ends with suffix
     using std::string::ends_with;
-
-    POPPLER_PRIVATE_EXPORT void prependUnicodeMarker();
 };
 
 #endif
diff --git a/poppler/Annot.cc b/poppler/Annot.cc
index 5736c990..7841637c 100644
--- a/poppler/Annot.cc
+++ b/poppler/Annot.cc
@@ -1504,7 +1504,7 @@ void Annot::setContents(std::unique_ptr<GooString> &&new_content)
         contents = std::move(new_content);
         // append the unicode marker <FE FF> if needed
         if (!hasUnicodeByteOrderMark(contents->toStr())) {
-            contents->prependUnicodeMarker();
+            prependUnicodeByteOrderMark(contents->toNonConstStr());
         }
     } else {
         contents = std::make_unique<GooString>();
@@ -2211,7 +2211,7 @@ void AnnotMarkup::setLabel(std::unique_ptr<GooString> &&new_label)
         label = std::move(new_label);
         // append the unicode marker <FE FF> if needed
         if (!hasUnicodeByteOrderMark(label->toStr())) {
-            label->prependUnicodeMarker();
+            prependUnicodeByteOrderMark(label->toNonConstStr());
         }
     } else {
         label = std::make_unique<GooString>();
@@ -2936,7 +2936,7 @@ void AnnotFreeText::setStyleString(GooString *new_string)
         styleString = std::make_unique<GooString>(new_string);
         // append the unicode marker <FE FF> if needed
         if (!hasUnicodeByteOrderMark(styleString->toStr())) {
-            styleString->prependUnicodeMarker();
+            prependUnicodeByteOrderMark(styleString->toNonConstStr());
         }
     } else {
         styleString = std::make_unique<GooString>();
@@ -3058,7 +3058,7 @@ public:
                     // Here we just layout one char, we don't know if the one afterwards can be layouted with the original font
                     GooString auxContents = GooString(text->toStr().substr(i, isUnicode ? 2 : 1));
                     if (isUnicode) {
-                        auxContents.prependUnicodeMarker();
+                        prependUnicodeByteOrderMark(auxContents.toNonConstStr());
                     }
                     int auxI = 0;
                     Annot::layoutText(&auxContents, &outputText, &auxI, *auxFont, &blockWidth, availableWidth ? *availableWidth : 0.0, &charCount, false, &newFontNeeded);
@@ -3145,7 +3145,7 @@ double Annot::calculateFontSize(const Form *form, const GfxFont *font, const Goo
         while (i < text->getLength()) {
             GooString lineText(text->toStr().substr(i));
             if (!hasUnicodeByteOrderMark(lineText.toStr()) && isUnicode) {
-                lineText.prependUnicodeMarker();
+                prependUnicodeByteOrderMark(lineText.toNonConstStr());
             }
             const HorizontalTextLayouter textLayouter(&lineText, form, font, availableWidthInFontSize, forceZapfDingbats);
             y -= fontSize;
@@ -3181,7 +3181,7 @@ static DrawMultiLineTextResult drawMultiLineText(const GooString &text, double a
     while (i < text.getLength()) {
         GooString lineText(text.toStr().substr(i));
         if (!hasUnicodeByteOrderMark(lineText.toStr()) && hasUnicodeByteOrderMark(text.toStr())) {
-            lineText.prependUnicodeMarker();
+            prependUnicodeByteOrderMark(lineText.toNonConstStr());
         }
         const HorizontalTextLayouter textLayouter(&lineText, form, &font, availableTextWidthInFontPtSize, false);
 
diff --git a/poppler/Form.cc b/poppler/Form.cc
index 3acf81f5..985f4870 100644
--- a/poppler/Form.cc
+++ b/poppler/Form.cc
@@ -1308,7 +1308,7 @@ GooString *FormField::getFullyQualifiedName()
     }
 
     if (unicode_encoded) {
-        fullyQualifiedName->prependUnicodeMarker();
+        prependUnicodeByteOrderMark(fullyQualifiedName->toNonConstStr());
     }
 
     return fullyQualifiedName;
@@ -1718,7 +1718,7 @@ void FormFieldText::setContentCopy(const GooString *new_content)
 
         // append the unicode marker <FE FF> if needed
         if (!hasUnicodeByteOrderMark(content->toStr())) {
-            content->prependUnicodeMarker();
+            prependUnicodeByteOrderMark(content->toNonConstStr());
         }
         Form *form = doc->getCatalog()->getForm();
         if (form) {
@@ -2167,7 +2167,7 @@ void FormFieldChoice::setEditChoice(const GooString *new_content)
 
         // append the unicode marker <FE FF> if needed
         if (!hasUnicodeByteOrderMark(editedChoice->toStr())) {
-            editedChoice->prependUnicodeMarker();
+            prependUnicodeByteOrderMark(editedChoice->toNonConstStr());
         }
     }
     updateSelection();
diff --git a/poppler/UTF.h b/poppler/UTF.h
index 812506eb..74c31cd3 100644
--- a/poppler/UTF.h
+++ b/poppler/UTF.h
@@ -63,6 +63,12 @@ inline bool hasUnicodeByteOrderMarkLE(const std::string &s)
     return s.starts_with(unicodeByteOrderMarkLE);
 }
 
+// put big-endian unicode byte order mark at the beginning of a string
+inline void prependUnicodeByteOrderMark(std::string &s)
+{
+    s.insert(0, unicodeByteOrderMark);
+}
+
 // is a unicode whitespace character
 bool UnicodeIsWhitespace(Unicode ucs4);