Merge pull request #2 from tiptenbrink/textwrap-len

_find_width_index and _handle_long_word change

Author: xi

Lib/test/test_textwrap.py

@@ -1118,5 +1118,31 @@ def test_shorten_placeholder(self):
                            text_len=self.text_len)
 
 
+class CustomWidthTestCase(BaseTestCase):
+    def text_len(self, text):
+        lengths = {
+            'A': 4,
+            'B': 2,
+            'Q': 0,
+        }
+
+        return sum(
+            lengths[c] if c in lengths else 1
+            for c in text
+        )
+
+    def test_zero_width_text_len(self):
+        text = "0QQ1234QQ56789"
+        self.check_wrap(text, 6, ["0QQ1234QQ5", "6789"], text_len=self.text_len)
+
+    def test_char_longer_than_width(self):
+        text = "AA0123"
+        self.check_wrap(text, 3, ["A", "A", "012", "3"], text_len=self.text_len)
+
+    def test_next_char_overflow(self):
+        text = "BB0123"
+        self.check_wrap(text, 3, ["B", "B0", "123"], text_len=self.text_len)
+
+
 if __name__ == '__main__':
     unittest.main()

Lib/textwrap.py

@@ -199,6 +199,25 @@ def _fix_sentence_endings(self, chunks):
             else:
                 i += 1
 
+    def _find_width_index(self, text, width):
+        """_find_length_index(text : string, width : int)
+
+        Find at which index the text has the required width, since when using a
+        different text_len, this index will not be equal to the required width.
+        """
+        # When using default len as self.text_len, the required index and width
+        # will be equal, this prevents calculation time.
+        if self.text_len(text[:width]) == width:
+            # For character widths greater than one, width can be more than the
+            # number of characters
+            return min(width, len(text))
+        cur_text = ''
+        for i, c in enumerate(text):
+            cur_text += c
+            cur_width = self.text_len(cur_text)
+            if cur_width > width:
+                return max(i, 1)
+
     def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
         """_handle_long_word(chunks : [string],
                              cur_line : [string],
@@ -217,12 +236,12 @@ def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
         # If we're allowed to break long words, then do so: put as much
         # of the next chunk onto the current line as will fit.
         if self.break_long_words:
-            end = space_left
             chunk = reversed_chunks[-1]
+            end = self._find_width_index(chunk, space_left)
             if self.break_on_hyphens and self.text_len(chunk) > space_left:
                 # break after last hyphen, but only if there are
                 # non-hyphens before it
-                hyphen = chunk.rfind('-', 0, space_left)
+                hyphen = chunk.rfind('-', 0, end)
                 if hyphen > 0 and any(c != '-' for c in chunk[:hyphen]):
                     end = hyphen + 1
             cur_line.append(chunk[:end])