Conversion pipeline: Add option to control if duplicate entries are allowed when generating the Table of Contents from links. Fixes #806095 ([Enhancement] Preserve duplicate chapter names in TOC)

src/calibre/ebooks/conversion/cli.py

@@ -176,7 +176,7 @@ def add_pipeline_options(parser, plumber):
                   [
                     'level1_toc', 'level2_toc', 'level3_toc',
                     'toc_threshold', 'max_toc_links', 'no_chapters_in_toc',
-                    'use_auto_toc', 'toc_filter',
+                    'use_auto_toc', 'toc_filter', 'duplicate_links_in_toc',
                   ]
                   ),
 

src/calibre/ebooks/conversion/plumber.py

@@ -265,6 +265,14 @@ OptionRecommendation(name='toc_filter',
                 )
         ),
 
+OptionRecommendation(name='duplicate_links_in_toc',
+            recommended_value=False, level=OptionRecommendation.LOW,
+            help=_('When creating a TOC from links in the input document, '
+                'allow duplicate entries, i.e. allow more than one entry '
+                'with the same text, provided that they point to a '
+                'different location.')
+        ),
+
 
 OptionRecommendation(name='chapter',
         recommended_value="//*[((name()='h1' or name()='h2') and "

src/calibre/ebooks/oeb/transforms/structure.py

@@ -121,14 +121,16 @@ class DetectStructure(object):
                     if not self.oeb.toc.has_href(href):
                         text = xml2text(a)
                         text = text[:100].strip()
-                        if not self.oeb.toc.has_text(text):
-                            num += 1
-                            self.oeb.toc.add(text, href,
-                                play_order=self.oeb.toc.next_play_order())
-                            if self.opts.max_toc_links > 0 and \
-                                    num >= self.opts.max_toc_links:
-                                self.log('Maximum TOC links reached, stopping.')
-                                return
+                        if (not self.opts.duplicate_links_in_toc and
+                                self.oeb.toc.has_text(text)):
+                            continue
+                        num += 1
+                        self.oeb.toc.add(text, href,
+                            play_order=self.oeb.toc.next_play_order())
+                        if self.opts.max_toc_links > 0 and \
+                                num >= self.opts.max_toc_links:
+                            self.log('Maximum TOC links reached, stopping.')
+                            return
 
 
 

src/calibre/gui2/convert/toc.py

@@ -22,7 +22,7 @@ class TOCWidget(Widget, Ui_Form):
         Widget.__init__(self, parent,
                 ['level1_toc', 'level2_toc', 'level3_toc',
                 'toc_threshold', 'max_toc_links', 'no_chapters_in_toc',
-                'use_auto_toc', 'toc_filter',
+                'use_auto_toc', 'toc_filter', 'duplicate_links_in_toc',
                 ]
                 )
         self.db, self.book_id = db, book_id

src/calibre/gui2/convert/toc.ui

@@ -21,7 +21,7 @@
      </property>
     </widget>
    </item>
-   <item row="2" column="0">
+   <item row="3" column="0">
     <widget class="QLabel" name="label_10">
      <property name="text">
       <string>Number of &amp;links to add to Table of Contents</string>
@@ -31,14 +31,14 @@
      </property>
     </widget>
    </item>
-   <item row="2" column="1">
+   <item row="3" column="1">
     <widget class="QSpinBox" name="opt_max_toc_links">
      <property name="maximum">
       <number>10000</number>
      </property>
     </widget>
    </item>
-   <item row="3" column="0">
+   <item row="4" column="0">
     <widget class="QLabel" name="label_16">
      <property name="text">
       <string>Chapter &amp;threshold</string>
@@ -48,7 +48,7 @@
      </property>
     </widget>
    </item>
-   <item row="3" column="1">
+   <item row="4" column="1">
     <widget class="QSpinBox" name="opt_toc_threshold"/>
    </item>
    <item row="0" column="0" colspan="2">
@@ -58,7 +58,7 @@
      </property>
     </widget>
    </item>
-   <item row="4" column="0">
+   <item row="5" column="0">
     <widget class="QLabel" name="label">
      <property name="text">
       <string>TOC &amp;Filter:</string>
@@ -68,19 +68,19 @@
      </property>
     </widget>
    </item>
-   <item row="4" column="1">
+   <item row="5" column="1">
     <widget class="QLineEdit" name="opt_toc_filter"/>
    </item>
-   <item row="5" column="0" colspan="2">
+   <item row="6" column="0" colspan="2">
     <widget class="XPathEdit" name="opt_level1_toc" native="true"/>
    </item>
-   <item row="6" column="0" colspan="2">
+   <item row="7" column="0" colspan="2">
     <widget class="XPathEdit" name="opt_level2_toc" native="true"/>
    </item>
-   <item row="7" column="0" colspan="2">
+   <item row="8" column="0" colspan="2">
     <widget class="XPathEdit" name="opt_level3_toc" native="true"/>
    </item>
-   <item row="8" column="0">
+   <item row="9" column="0">
     <spacer name="verticalSpacer">
      <property name="orientation">
       <enum>Qt::Vertical</enum>
@@ -93,6 +93,13 @@
      </property>
     </spacer>
    </item>
+   <item row="2" column="0" colspan="2">
+    <widget class="QCheckBox" name="opt_duplicate_links_in_toc">
+     <property name="text">
+      <string>Allow &amp;duplicate links when creating the Table of Contents</string>
+     </property>
+    </widget>
+   </item>
   </layout>
  </widget>
  <customwidgets>