strongs: output code as superscript

1 files changed, 16 insertions, 4 deletions

diff --git a/usfm2gmi.py b/usfm2gmi.py
index fb25131..43a8c87 100755
--- a/usfm2gmi.py
+++ b/usfm2gmi.py
@@ -21,10 +21,21 @@ def smallcaps(word):
       new += c
   return new
 
+def superscript(word):
+  #TODO: also superscript lowercase letters
+  ss='⁰¹²³⁴⁵⁶⁷⁸⁹:;<=>?@ᴬᴮCᴰᴱFᴳᴴᶦᴶᴷᴸᴹᴺᴼᴾQᴿSᵀᵁⱽᵂ'
+  new = ''
+  for c in word:
+    if c >= '0' and c <= 'W':
+      new += ss[ord(c)-ord('0')]
+    else:
+      new += c
+  return new
+
 def convert(line):
   """Convert a string to a list of tuples, each a token"""
   # TODO: preserve the lack of whitespace before a backslash.
-  split = line.replace('\\', ' \\').replace('\\nd*','\\nd* ').replace('\\f*','\\f* ').replace('\\wj*','\\wj* ').replace('|strong',' |strong').split()
+  split = line.replace('\\', ' \\').replace('\\nd*','\\nd* ').replace('\\f*','\\f* ').replace('\\wj*','\\wj* ').replace('\\w*','\\w* ').split()
   out = ''
   nd = False
   if len(split) == 0:
@@ -83,10 +94,11 @@ def convert(line):
     # TODO: support Endnotes (\fe and \fe*)
     elif word in ['\\ft']:
       continue # TODO: fancy formatting of more types
-    elif word == '\\w':
-      continue
-    elif '|strong' in word:
+    elif word in ['\\w','\\w*']:
       continue
+    elif '|strong="' in word:
+      spl = word.split('|')
+      out += spl[0] + superscript(spl[1][8:-1]) + ' '
     else:
      if nd:
       out += smallcaps(word) + ' '