Add ppcomp option to suppress word join (U+2060) (#18)

Fixes issue #17

ppcomp/ppcomp.py

@@ -586,13 +586,16 @@ def remove_nbspaces(self):
         """Remove non-breakable spaces between numbers. For instance, a
         text file could have 250000, and the html could have 250 000.
         """
-        # Todo:  ,  ,  ?
         if self.args.suppress_nbsp_num:
             self.text = re.sub(r"(\d)\u00A0(\d)", r"\1\2", self.text)
 
+    def remove_wordjoin(self):
+        """Remove word join (NoBreak) (U+2060)."""
+        if self.args.suppress_word_join:
+            self.text = re.sub(r"\u2060", r"", self.text)
+
     def remove_soft_hyphen(self):
         """Suppress shy (soft hyphen)"""
-        # Todo: ­, ­?
         self.text = re.sub(r"\u00AD", r"", self.text)
 
     def cleanup(self):
@@ -617,6 +620,7 @@ def cleanup(self):
 
         self.remove_nbspaces()
         self.remove_soft_hyphen()
+        self.remove_wordjoin()
 
     @staticmethod
     def _text_transform(val, errors: list):
@@ -1121,6 +1125,8 @@ def main():
                         help="HTML: do not use default transformation CSS")
     parser.add_argument('--suppress-nbsp-num', action='store_true', default=False,
                         help="HTML: Suppress non-breakable spaces between numbers")
+    parser.add_argument('--suppress-word-join', action='store_true', default=False,
+                        help="HTML: Suppress word join (NoBreak) (U+2060)")
     parser.add_argument('--ignore-0-space', action='store_true', default=False,
                         help='HTML: suppress zero width space (U+200b)')
     parser.add_argument('--css-greek-title-plus', action='store_true', default=False,

tests/fossilplants1.html

@@ -5419,7 +5419,7 @@ <h2 class="nobreak" id="CHAPTER_V">CHAPTER V.</h2>
 
   <p><span class="pagenum" id="Page_98">98</span></p>
 
-  <p>Endless examples might be quoted illustrating the absolute futility,
+  <p>Endless examples might be quoted&#8288; illustrating the absolute futility,
     in many cases, of relying on external features even for the purpose
     of class distinction. An acquaintance with the general habit and
     appearance of only the better known members of a family, frequently
@@ -5476,7 +5476,7 @@ <h2 class="nobreak" id="CHAPTER_V">CHAPTER V.</h2>
     correspond in the character of their venation to Monocotyledonous
     leaves. <i>Eryngium montanum</i> Coult., <i>E. Lassauxi</i> Dcne., and
     other species of this genus of <i>Umbelliferæ</i> agree closely with
-    such a plant as <i>Pandanus</i> or other Monocotyledons; similarly
+    such a plant as <i>Pandanus</i> or other Monocotyledons&#8288;; similarly
     the long linear leaves of <i>Richea dracophylla</i>, R. Br., one
     of the Ericaceæ, are identical in form with many monocotyledonous
     leaves. Instances might also be quoted of monocotyledonous leaves,

tests/test_ppcomp.py

@@ -242,6 +242,12 @@ def test_remove_nbspaces():
     assert not re.search(r"(\d)\u00A0(\d)", html_file.text)
     assert 0 <= html_file.text.find("2885")
 
+def test_suppress_word_join():
+    args = myargs + ['--suppress-word-join']
+    html_file = PgdpFileHtml(load_args(args))
+    html_file.load('fossilplants1.html')
+    html_file.remove_nbspaces()
+    assert not re.search(r"\u2060", html_file.text)
 
 def test_remove_soft_hyphen():
     html_file = PgdpFileHtml(load_args(myargs))
@@ -401,6 +407,8 @@ def load_args(myargs):
                         help="HTML: do not use default transformation CSS")
     parser.add_argument('--suppress-nbsp-num', action='store_true', default=False,
                         help="HTML: Suppress non-breakable spaces between numbers")
+    parser.add_argument('--suppress-word-join', action='store_true', default=False,
+                        help="HTML: Suppress word join (NoBreak) (U+2060)")
     parser.add_argument('--ignore-0-space', action='store_true', default=False,
                         help='HTML: suppress zero width space (U+200b)')
     parser.add_argument('--css-greek-title-plus', action='store_true', default=False,