Hints kitten: validate IPs with ipaddress

On the initial commit of this feature, IPs were just matched with a
very simple regex that prioritised simplicity/readability over
accuracy.

This commit adds a postprocessor for ip matches that makes use of
Python's `ipaddress` in the standard library to validate all the IP
matches.

This way we don't need huge and complex regex patterns to match _and_
validate the IPs, and we can just use `ipaddress` to abstract us from
implementing all the validation logic into the regex pattern.

kittens/hints/main.py

@@ -2,6 +2,7 @@
 # vim:fileencoding=utf-8
 # License: GPL v3 Copyright: 2018, Kovid Goyal <kovid at kovidgoyal.net>
 
+import ipaddress
 import os
 import re
 import string
@@ -236,6 +237,11 @@ def postprocessor(func: PostprocessorFunc) -> PostprocessorFunc:
     return func
 
 
+class InvalidMatch(Exception):
+    """Raised when a match turns out to be invalid."""
+    pass
+
+
 @postprocessor
 def url(text: str, s: int, e: int) -> Tuple[int, int]:
     if s > 4 and text[s - 5:s] == 'link:':  # asciidoc URLs
@@ -280,11 +286,28 @@ def quotes(text: str, s: int, e: int) -> Tuple[int, int]:
     return s, e
 
 
+@postprocessor
+def ip(text: str, s: int, e: int) -> Tuple[int, int]:
+    # Check validity of IPs (or raise InvalidMatch)
+    ip = text[s:e]
+
+    try:
+        ipaddress.ip_address(ip)
+    except ValueError:
+        raise InvalidMatch("Invalid IP")
+
+    return s, e
+
+
 def mark(pattern: str, post_processors: Iterable[PostprocessorFunc], text: str, args: HintsCLIOptions) -> Generator[Mark, None, None]:
     pat = re.compile(pattern)
     for idx, (s, e, groupdict) in enumerate(regex_finditer(pat, args.minimum_match_length, text)):
-        for func in post_processors:
-            s, e = func(text, s, e)
+        try:
+            for func in post_processors:
+                s, e = func(text, s, e)
+        except InvalidMatch:
+            continue
+
         mark_text = text[s:e].replace('\n', '').replace('\0', '')
         yield Mark(idx, s, e, mark_text, groupdict)
 
@@ -333,6 +356,7 @@ def functions_for(args: HintsCLIOptions) -> Tuple[str, List[PostprocessorFunc]]:
             # # IPv6 with no validation
             r"(?:[a-fA-F0-9]{0,4}:){2,7}[a-fA-F0-9]{1,4})"
         )
+        post_processors.append(ip)
     elif args.type == 'word':
         chars = args.word_characters
         if chars is None:

kitty_tests/hints.py

@@ -48,8 +48,9 @@ class TestHints(BaseTest):
             ('2001:DB8::FF00:42:8329', ['2001:DB8::FF00:42:8329']),
             ('0000:0000:0000:0000:0000:0000:0000:0001', ['0000:0000:0000:0000:0000:0000:0000:0001']),
             ('::1', ['::1']),
-            # The regex doesn't check for validity
-            ('255.255.255.256', ['255.255.255.256']),
+            # Invalid IPs won't match
+            ('255.255.255.256', []),
+            (':1', []),
         )
 
         for testcase, expected in testcases: