tdf#97198 Make Calc function LEN work with Unicode non-BMP characters.

Change-Id: Ibfdaaf1ed313257fc5f9036a7dd1ef51033fa8cd
Reviewed-on: https://gerrit.libreoffice.org/44681
Tested-by: Jenkins <ci@libreoffice.org>
Reviewed-by: Eike Rathke <erack@redhat.com>

2 files changed, 102 insertions, 8 deletions

diff --git a/sc/qa/unit/data/functions/text/fods/len.fods b/sc/qa/unit/data/functions/text/fods/len.fods
index 2d643cef2fcd..adc36d87f379 100644
--- a/sc/qa/unit/data/functions/text/fods/len.fods
+++ b/sc/qa/unit/data/functions/text/fods/len.fods
@@ -1189,13 +1189,99 @@
      <table:table-cell table:style-name="ce17"/>
      <table:table-cell table:number-columns-repeated="4"/>
     </table:table-row>
-    <table:table-row table:style-name="ro5" table:number-rows-repeated="28">
-     <table:table-cell table:style-name="ce14"/>
-     <table:table-cell table:style-name="ce17"/>
-     <table:table-cell table:style-name="ce27"/>
-     <table:table-cell table:style-name="ce11"/>
+    <table:table-row table:style-name="ro5">
+     <table:table-cell table:style-name="ce14" table:formula="of:=LEN([.I10])" office:value-type="float" office:value="16" calcext:value-type="float">
+      <text:p>16</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="float" office:value="16" calcext:value-type="float">
+      <text:p>16</text:p>
+     </table:table-cell>
+     <table:table-cell table:style-name="ce40" table:formula="of:=[.A10]=[.B10]" office:value-type="boolean" office:boolean-value="true" calcext:value-type="boolean">
+      <text:p>TRUE</text:p>
+     </table:table-cell>
+     <table:table-cell table:style-name="ce11" table:formula="of:=FORMULA([.A10])" office:value-type="string" office:string-value="=LEN(I10)" calcext:value-type="string">
+      <text:p>=LEN(I10)</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>Excel 2016 returns 25</text:p>
+     </table:table-cell>
+     <table:table-cell table:number-columns-repeated="3"/>
+     <table:table-cell office:value-type="string" calcext:value-type="string"><text:p>ab<text:span text:style-name="T1">😂de𝔖gh𝕬𝖈𝖍𝖙𝖚𝖓𝖌!</text:span></text:p>
+     </table:table-cell>
      <table:table-cell table:number-columns-repeated="4"/>
-     <table:table-cell table:style-name="ce17"/>
+    </table:table-row>
+    <table:table-row table:style-name="ro5">
+     <table:table-cell table:style-name="ce14" table:formula="of:=LEN([.I11])" office:value-type="float" office:value="3" calcext:value-type="float">
+      <text:p>3</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="float" office:value="3" calcext:value-type="float">
+      <text:p>3</text:p>
+     </table:table-cell>
+     <table:table-cell table:style-name="ce41" table:formula="of:=[.A11]=[.B11]" office:value-type="boolean" office:boolean-value="true" calcext:value-type="boolean">
+      <text:p>TRUE</text:p>
+     </table:table-cell>
+     <table:table-cell table:style-name="ce11" table:formula="of:=FORMULA([.A11])" office:value-type="string" office:string-value="=LEN(I11)" calcext:value-type="string">
+      <text:p>=LEN(I11)</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>Excel 2016 returns 4</text:p>
+     </table:table-cell>
+     <table:table-cell table:number-columns-repeated="3"/>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>ab😂</text:p>
+     </table:table-cell>
+     <table:table-cell table:number-columns-repeated="4"/>
+    </table:table-row>
+    <table:table-row table:style-name="ro5">
+     <table:table-cell table:style-name="ce14" table:formula="of:=LEN([.I12])" office:value-type="float" office:value="4" calcext:value-type="float">
+      <text:p>4</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="float" office:value="4" calcext:value-type="float">
+      <text:p>4</text:p>
+     </table:table-cell>
+     <table:table-cell table:style-name="ce42" table:formula="of:=[.A12]=[.B12]" office:value-type="boolean" office:boolean-value="true" calcext:value-type="boolean">
+      <text:p>TRUE</text:p>
+     </table:table-cell>
+     <table:table-cell table:style-name="ce11" table:formula="of:=FORMULA([.A12])" office:value-type="string" office:string-value="=LEN(I12)" calcext:value-type="string">
+      <text:p>=LEN(I12)</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>Excel 2016 returns 6</text:p>
+     </table:table-cell>
+     <table:table-cell table:number-columns-repeated="3"/>
+     <table:table-cell table:style-name="ce44" office:value-type="string" calcext:value-type="string"><text:p><text:span text:style-name="T2">&quot;</text:span><text:span text:style-name="T3">𧌒𧀬</text:span><text:span text:style-name="T4">&quot;</text:span></text:p>
+     </table:table-cell>
+     <table:table-cell table:number-columns-repeated="4"/>
+    </table:table-row>
+    <table:table-row table:style-name="ro3">
+     <table:table-cell table:style-name="ce14" table:formula="of:=LEN([.I13])" office:value-type="float" office:value="6" calcext:value-type="float">
+      <text:p>6</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="float" office:value="6" calcext:value-type="float">
+      <text:p>6</text:p>
+     </table:table-cell>
+     <table:table-cell table:style-name="ce45" table:formula="of:=[.A13]=[.B13]" office:value-type="boolean" office:boolean-value="true" calcext:value-type="boolean">
+      <text:p>TRUE</text:p>
+     </table:table-cell>
+     <table:table-cell table:style-name="ce11" table:formula="of:=FORMULA([.A13])" office:value-type="string" office:string-value="=LEN(I13)" calcext:value-type="string">
+      <text:p>=LEN(I13)</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>Excel 2016 returns 6</text:p>
+     </table:table-cell>
+     <table:table-cell table:number-columns-repeated="3"/>
+     <table:table-cell table:style-name="ce48" office:value-type="string" calcext:value-type="string">
+      <text:p>&quot;üë&quot;</text:p>
+     </table:table-cell>
+     <table:table-cell table:number-columns-repeated="4"/>
+    </table:table-row>
+    <table:table-row table:style-name="ro5" table:number-rows-repeated="24">
+      <table:table-cell table:style-name="ce14"/>
+      <table:table-cell table:style-name="ce17"/>
+     <table:table-cell table:style-name="ce38"/>
+      <table:table-cell table:style-name="ce11"/>
+      <table:table-cell table:number-columns-repeated="4"/>
+      <table:table-cell table:style-name="ce17"/>
      <table:table-cell table:number-columns-repeated="4"/>
     </table:table-row>
     <table:table-row table:style-name="ro2" table:number-rows-repeated="39">
@@ -1232,4 +1318,4 @@
    </table:named-expressions>
   </office:spreadsheet>
  </office:body>
-</office:document>
\ No newline at end of file
+</office:document>
diff --git a/sc/source/core/tool/interpr1.cxx b/sc/source/core/tool/interpr1.cxx
index f83040c79e39..96d8f764a418 100644
--- a/sc/source/core/tool/interpr1.cxx
+++ b/sc/source/core/tool/interpr1.cxx
@@ -3064,7 +3064,15 @@ void ScInterpreter::ScLower()
 
 void ScInterpreter::ScLen()
 {
-    PushDouble(GetString().getLength());
+    OUString aStr = GetString().getString();
+    sal_Int32 nIdx = 0;
+    sal_Int32 nCnt = 0;
+    while ( nIdx < aStr.getLength() )
+    {
+        aStr.iterateCodePoints( &nIdx );
+        ++nCnt;
+    }
+    PushDouble( nCnt );
 }
 
 void ScInterpreter::ScT()