Update tokenizer and html converter

2019-10-25 00:07:37 +02:00
parent a67d3ed599
commit 01dde7c8a4
2 changed files with 30 additions and 22 deletions
@@ -28,9 +28,13 @@ class ToHtml(Tokenizer):
        Tokenizer.doAutoReplace(self)

        repDict = {
-            "<" : "&lt;",
-            ">" : "&gt;",
-            "&" : "&amp;",
+            "<"      : "&lt;",
+            ">"      : "&gt;",
+            "&"      : "&amp;",
+            "\u2013" : "&endash;",
+            "\u2014" : "$emdash;",
+            "\u2500" : "$emdash;",
+            "\u2026" : "&hellip;",
        }
        xRep = re.compile("|".join([re.escape(k) for k in repDict.keys()]), flags=re.DOTALL)
        self.theText = xRep.sub(lambda x: repDict[x.group(0)], self.theText)