ENG-74: refine credit inference regex

This commit refines the regex for inferring credit directions. It ultimately removes requirements for names (the part after the word "by") due to the inordinate difficulty of writing strict regex that catches all possible characters included in names. To mitigate false positives, it clarifies/restricts the regex for the part before the word "by". This compromise decreases the number of false negatives without significantly increasing false positives. Duplicate of musescore#8678, part 3
Jojo-Schmitz · Jul 28, 2021 · 3406ada · 3406ada
1 parent 526dff2
commit 3406ada
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 3 deletions.
diff --git a/importexport/musicxml/importmxmlpass2.cpp b/importexport/musicxml/importmxmlpass2.cpp
@@ -3385,7 +3385,7 @@ bool MusicXMLParserDirection::isLikelyCredit(const Fraction& tick) const
             && _rehearsalText == ""
             && _metroText == ""
             && _tpoSound < 0.1
-            && _wordsText.contains(QRegularExpression("^\\s*((Words|Music|Lyrics).*)*by\\s+([A-Z][a-zA-Zö'’-]+\\s[A-Z][a-zA-Zös'’-]+.*)+"));
+            && _wordsText.contains(QRegularExpression("^\\s*((Words|Music|Lyrics),?(\\sand|\\s&amp;)?\\s)*[Bb]y\\s+(?!$)"));
       }
 
 //---------------------------------------------------------

diff --git a/mtest/musicxml/io/testInferredCredits.xml b/mtest/musicxml/io/testInferredCredits.xml
@@ -87,13 +87,19 @@
         </attributes>
       <direction placement="above">
         <direction-type>
-          <words default-y="34.66" relative-y="10.00">Words and Music by Henry Ives
+          <words default-y="34.66" relative-y="10.00">Words &amp; Music by Henry Ives (and ampersands)
 </words>
           <words>
 </words>
           <words></words>
           </direction-type>
         </direction>
+      <direction placement="above">
+        <direction-type>
+          <words default-y="34.66" relative-y="10.00">Lyrics to be sung by candlelight
+(and this not to be inferred)</words>
+          </direction-type>
+        </direction>
       <note default-x="73.72" default-y="-15.00">
         <pitch>
           <step>C</step>

diff --git a/mtest/musicxml/io/testInferredCredits_ref.mscx b/mtest/musicxml/io/testInferredCredits_ref.mscx
@@ -125,7 +125,7 @@
           </Text>
         <Text>
           <style>Composer</style>
-          <text>Words and Music by Henry Ives</text>
+          <text>Words &amp; Music by Henry Ives (and ampersands)</text>
           </Text>
         <Text>
           <style>Subtitle</style>
@@ -143,6 +143,10 @@ the video game: a tone poem</text>
             <sigN>4</sigN>
             <sigD>4</sigD>
             </TimeSig>
+          <StaffText>
+            <text>Lyrics to be sung by candlelight
+(and this not to be inferred)</text>
+            </StaffText>
           <Beam>
             <StemDirection>down</StemDirection>
             <l1>17</l1>