Refactor strip_email_quotes

MrMino · MrMino · commit c20d7a0da79b · 2021-06-30T17:20:34.000+02:00
Also removes long_substr, which fixes the licesing issue mentioned in #13039.
diff --git a/IPython/utils/tests/test_text.py b/IPython/utils/tests/test_text.py
@@ -165,19 +165,6 @@ def test_dollar_formatter():
     nt.assert_equal(s, "$HOME")
 
 
-def test_long_substr():
-    data = ['hi']
-    nt.assert_equal(text.long_substr(data), 'hi')
-
-
-def test_long_substr2():
-    data = ['abc', 'abd', 'abf', 'ab']
-    nt.assert_equal(text.long_substr(data), 'ab')
-
-def test_long_substr_empty():
-    data = []
-    nt.assert_equal(text.long_substr(data), '')
-
 def test_strip_email():
     src = """\
         >> >>> def f(x):
diff --git a/IPython/utils/text.py b/IPython/utils/text.py
@@ -10,6 +10,7 @@
 
 import os
 import re
+import string
 import sys
 import textwrap
 from string import Formatter
@@ -405,22 +406,6 @@ def wrap_paragraphs(text, ncols=80):
     return out_ps
 
 
-def long_substr(data):
-    """Return the longest common substring in a list of strings.
-
-    Credit: http://stackoverflow.com/questions/2892931/longest-common-substring-from-more-than-two-strings-python
-    """
-    substr = ''
-    if len(data) > 1 and len(data[0]) > 0:
-        for i in range(len(data[0])):
-            for j in range(len(data[0])-i+1):
-                if j > len(substr) and all(data[0][i:i+j] in x for x in data):
-                    substr = data[0][i:i+j]
-    elif len(data) == 1:
-        substr = data[0]
-    return substr
-
-
 def strip_email_quotes(text):
     """Strip leading email quotation characters ('>').
 
@@ -447,27 +432,30 @@ def strip_email_quotes(text):
         In [4]: strip_email_quotes('> > text\\n> > more\\n> more...')
         Out[4]: '> text\\n> more\\nmore...'
 
-    So if any line has no quote marks ('>') , then none are stripped from any
+    So if any line has no quote marks ('>'), then none are stripped from any
     of them ::
-    
+
         In [5]: strip_email_quotes('> > text\\n> > more\\nlast different')
         Out[5]: '> > text\\n> > more\\nlast different'
     """
     lines = text.splitlines()
-    matches = set()
-    for line in lines:
-        prefix = re.match(r'^(\s*>[ >]*)', line)
-        if prefix:
-            matches.add(prefix.group(1))
+    strip_len = 0
+
+    for characters in zip(*lines):
+        # Check if all characters in this position are the same
+        if len(set(characters)) > 1:
+            break
+        prefix_char = characters[0][0]
+
+        if prefix_char in string.whitespace or prefix_char == ">":
+            strip_len += 1
         else:
             break
-    else:
-        prefix = long_substr(list(matches))
-        if prefix:
-            strip = len(prefix)
-            text = '\n'.join([ ln[strip:] for ln in lines])
+
+    text = "\n".join([ln[strip_len:] for ln in lines])
     return text
 
+
 def strip_ansi(source):
     """
     Remove ansi escape codes from text.
