Data commit

Task/Read-a-file-character-by-character-UTF8/Python/read-a-file-character-by-character-utf8-1.py

@@ -0,0 +1,20 @@
+def get_next_character(f):
+  # note: assumes valid utf-8
+  c = f.read(1)
+  while c:
+    while True:
+      try:
+        yield c.decode('utf-8')
+      except UnicodeDecodeError:
+        # we've encountered a multibyte character
+        # read another byte and try again
+        c += f.read(1)
+      else:
+        # c was a valid char, and was yielded, continue
+        c = f.read(1)
+        break
+
+# Usage:
+with open("input.txt","rb") as f:
+    for c in get_next_character(f):
+        print(c)

Task/Read-a-file-character-by-character-UTF8/Python/read-a-file-character-by-character-utf8-2.py

@@ -0,0 +1,11 @@
+def get_next_character(f):
+    """Reads one character from the given textfile"""
+    c = f.read(1)
+    while c:
+        yield c
+        c = f.read(1)
+
+# Usage:
+with open("input.txt", encoding="utf-8") as f:
+    for c in get_next_character(f):
+        print(c, sep="", end="")