tdf#161737 i18npool: fix fake spelling alarms with NNBSP

Fix word break by excluding narrow no-break space at the
end of the words for spell checking.

This was a problem e.g. for French, where (automatically? or
manually) inserted narrow no-break space is used to get correct
typography before exclamation and question marks, also after and
before guillemets, if the OpenType/Graphite font doesn't have this
feature).

Regression from commit 44699b3de37f07090ac6fee1cd97aa76036e9700
"tdf#49885 BreakIterator rule upgrades".

Note: this fixes also the problem, when digits separated
by NNBSP thousand separator weren't handled by spell checking,
alarming fake spelling mistakes, when "Check words with numbers"
was enabled in Tools->Options->Languages and Locales->Writing Aids.
(TODO: at the case of thousand separators, remove NBSP by the
linguistic module or by the spell checking dictionaries to allow
to check numbers with thousand separators and with correct suffix.)

Change-Id: I36e10add7e0ba840f207a375ccc8668dbfef9572
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/169618
Tested-by: Jenkins
Reviewed-by: László Németh <nemeth@numbertext.org>

2 files changed, 31 insertions, 1 deletions

diff --git a/i18npool/qa/cppunit/test_breakiterator.cxx b/i18npool/qa/cppunit/test_breakiterator.cxx
index e790c17e1155..6fbde026f565 100644
--- a/i18npool/qa/cppunit/test_breakiterator.cxx
+++ b/i18npool/qa/cppunit/test_breakiterator.cxx
@@ -992,6 +992,36 @@ void TestBreakIterator::testWordBoundaries()
         CPPUNIT_ASSERT_EQUAL(sal_Int32(8), aBounds.startPos);
         CPPUNIT_ASSERT_EQUAL(sal_Int32(11), aBounds.endPos);
     }
+
+    //  tdf#161737: narrow no-break space at the end of words resulted spelling mistakes
+    {
+        aLocale.Language = "en";
+        aLocale.Country = "US";
+
+        OUString aTest(u"L’espace fine insécable\u202F!"_ustr);
+        aBounds
+            = m_xBreak->getWordBoundary(aTest, 14, aLocale, i18n::WordType::DICTIONARY_WORD, false);
+        CPPUNIT_ASSERT_EQUAL(sal_Int32(14), aBounds.startPos);
+        // This was 24 (word + NNBSP)
+        CPPUNIT_ASSERT_EQUAL(sal_Int32(23), aBounds.endPos);
+    }
+
+    //  tdf#161737: narrow no-break space between digits resulted spelling mistakes
+    //  as a quick fix, limit NBSP as word-part character only for editing, and not for spell checking
+    //  TODO: remove NBSP by the linguistic module or by the spell checking dictionaries to allow
+    //  to check numbers with thousand separators and with correct suffix
+    {
+        aLocale.Language = "en";
+        aLocale.Country = "US";
+
+        OUString aTest(u"1\u202F000\u202F000"_ustr);
+        aBounds
+            = m_xBreak->getWordBoundary(aTest, 2, aLocale, i18n::WordType::DICTIONARY_WORD, false);
+        // This was 0 (word + NNBSP)
+        CPPUNIT_ASSERT_EQUAL(sal_Int32(2), aBounds.startPos);
+        // This was 8 (word + NNBSP)
+        CPPUNIT_ASSERT_EQUAL(sal_Int32(5), aBounds.endPos);
+    }
 }
 
 void TestBreakIterator::testSentenceBoundaries()
diff --git a/i18npool/source/breakiterator/data/dict_word.txt b/i18npool/source/breakiterator/data/dict_word.txt
index f804b0eec214..deeec7dd659e 100644
--- a/i18npool/source/breakiterator/data/dict_word.txt
+++ b/i18npool/source/breakiterator/data/dict_word.txt
@@ -54,7 +54,7 @@ $Double_Quote       = [\p{Word_Break = Double_Quote}];
 $MidNumLet          = [\p{Word_Break = MidNumLet}];
 $MidNum             = [\p{Word_Break = MidNum}];
 $Numeric            = [\p{Word_Break = Numeric}];
-$ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
+$ExtendNumLet       = [\p{Word_Break = ExtendNumLet}-[:name = NARROW NO-BREAK SPACE:]];
 $WSegSpace          = [\p{Word_Break = WSegSpace}];
 $Extended_Pict      = [\p{Extended_Pictographic}];