sync with O'Reilly Atlas

04-text-byte/simplify.py

@@ -51,7 +51,7 @@ def shave_marks_latin(txt):
         if unicodedata.combining(c) and latin_base:   # <2>
             continue  # ignore diacritic on Latin base char
         preserve.append(c)                            # <3>
-        # if it isn't combining char, it's a new base char
+        # if it isn't a combining char, it's a new base char
         if not unicodedata.combining(c):              # <4>
             latin_base = c in string.ascii_letters
     shaved = ''.join(preserve)

04-text-byte/zwj_sample.py

@@ -18,8 +18,7 @@ for line in zwg_sample.strip().split('\n'):
     code, descr, version = (s.strip() for s in line.split('|'))
     chars = [chr(int(c, 16)) for c in code.split()]
     print(''.join(chars), version, descr, sep='\t', end='')
-    while chars:
-        char = chars.pop(0)
+    for char in chars:
         if char in markers:
             print(' + ' + markers[char], end='')
         else: