(generate_id) support Vietnamese accents

Vietnamese chars with accents will be converted to non-accent verion that help the link id (anchor name) readable
icyfork · Feb 9, 2013 · 7b7ac02 · 7b7ac02
1 parent 1fccba5
commit 7b7ac02
Show file tree

Hide file tree

Showing 3 changed files with 14 additions and 1 deletion.
diff --git a/lib/kramdown/converter/base.rb b/lib/kramdown/converter/base.rb
@@ -164,7 +164,16 @@ def extract_code_language!(attr)
       # Uses the option +auto_id_prefix+: the value of this option is prepended to every generated
       # ID.
       def generate_id(str)
-        gen_id = str.gsub(/^[^a-zA-Z]+/, '')
+        # Convert Vietnamese accents to non-accent version
+        # This will help the link readable
+        vntext_src =  "áàảãạăắằẳẵặâấầẩẫậđéèẻẽẹêếềểễệíìỉĩịóòỏõọôốồổỗộơớờởỡợúùủũụưứừửữựýỳỷỹỵ"
+        vntext_dst =  "aaaaaaaaaaaaaaaaadeeeeeeeeeeeiiiiioooooooooooooooouuuuuuuuuuuuyyyyy"
+        vntext_src += "ÁÀẢÃẠĂẮẰẲẴẶÂẤẦẨẪẬĐÉÈẺẼẸÊẾỀỂỄỆÍÌỈĨỊÓÒỎÕỌÔỐỒỔỖỘƠỚỜỞỠỢÚÙỦŨỤƯỨỪỬỮỰÝỲỶỸỴ"
+        vntext_dst += vntext_dst.upcase
+
+        gen_id = str
+        gen_id.tr!(vntext_src, vntext_dst)
+        gen_id.gsub!(/^[^a-zA-Z]+/, '')
         gen_id.tr!('^a-zA-Z0-9 -', '')
         gen_id.tr!(' ', '-')
         gen_id.downcase!

diff --git a/test/testcases/block/04_header/with_auto_ids.html b/test/testcases/block/04_header/with_auto_ids.html
@@ -17,3 +17,5 @@ <h1 id="section-1">33333</h1>
 <h2 id="hallo-2">hallO</h2>
 
 <h1>Header without ID</h1>
+
+<h1 id="day-la-vi-du-voi-tieng-viet">Đây là ví dụ với tiếng Việt</h1>
diff --git a/test/testcases/block/04_header/with_auto_ids.text b/test/testcases/block/04_header/with_auto_ids.text
@@ -20,3 +20,5 @@ Not now
 
 # Header without ID
 {: id=""}
+
+# Đây là ví dụ với tiếng Việt