ENH: Color matching wrong word in the interactive session (#2771)

Author: yarikoptic

codespell_lib/_codespell.py

@@ -23,7 +23,7 @@
 import re
 import sys
 import textwrap
-from typing import Dict, List, Optional, Pattern, Sequence, Set, Tuple
+from typing import Dict, List, Match, Optional, Pattern, Sequence, Set, Tuple
 
 # autogenerated by setuptools_scm
 from ._version import __version__ as VERSION
@@ -680,18 +680,26 @@ def fix_case(word: str, fixword: str) -> str:
 
 def ask_for_word_fix(
     line: str,
-    wrongword: str,
+    match: Match[str],
     misspelling: Misspelling,
     interactivity: int,
+    colors: TermColors,
 ) -> Tuple[bool, str]:
+    wrongword = match.group()
     if interactivity <= 0:
         return misspelling.fix, fix_case(wrongword, misspelling.data)
 
+    line_ui = (
+        f"{line[:match.start()]}"
+        f"{colors.WWORD}{wrongword}{colors.DISABLE}"
+        f"{line[match.end():]}"
+    )
+
     if misspelling.fix and interactivity & 1:
         r = ""
         fixword = fix_case(wrongword, misspelling.data)
         while not r:
-            print(f"{line}\t{wrongword} ==> {fixword} (Y/n) ", end="", flush=True)
+            print(f"{line_ui}\t{wrongword} ==> {fixword} (Y/n) ", end="", flush=True)
             r = sys.stdin.readline().strip().upper()
             if not r:
                 r = "Y"
@@ -709,7 +717,7 @@ def ask_for_word_fix(
         r = ""
         opt = [w.strip() for w in misspelling.data.split(",")]
         while not r:
-            print(f"{line} Choose an option (blank for none): ", end="")
+            print(f"{line_ui} Choose an option (blank for none): ", end="")
             for i, o in enumerate(opt):
                 fixword = fix_case(wrongword, o)
                 print(f" {i}) {fixword}", end="")
@@ -743,30 +751,50 @@ def print_context(
             print("{} {}".format(">" if i == index else ":", lines[i].rstrip()))
 
 
+def _ignore_word_sub(
+    text: str,
+    ignore_word_regex: Optional[Pattern[str]],
+) -> str:
+    if ignore_word_regex:
+        text = ignore_word_regex.sub(" ", text)
+    return text
+
+
 def extract_words(
     text: str,
     word_regex: Pattern[str],
     ignore_word_regex: Optional[Pattern[str]],
 ) -> List[str]:
-    if ignore_word_regex:
-        text = ignore_word_regex.sub(" ", text)
-    return word_regex.findall(text)
+    return word_regex.findall(_ignore_word_sub(text, ignore_word_regex))
+
+
+def extract_words_iter(
+    text: str,
+    word_regex: Pattern[str],
+    ignore_word_regex: Optional[Pattern[str]],
+) -> List[Match[str]]:
+    return list(word_regex.finditer(_ignore_word_sub(text, ignore_word_regex)))
 
 
 def apply_uri_ignore_words(
-    check_words: List[str],
+    check_matches: List[Match[str]],
     line: str,
     word_regex: Pattern[str],
     ignore_word_regex: Optional[Pattern[str]],
     uri_regex: Pattern[str],
     uri_ignore_words: Set[str],
-) -> None:
+) -> List[Match[str]]:
     if not uri_ignore_words:
-        return
+        return check_matches
     for uri in re.findall(uri_regex, line):
         for uri_word in extract_words(uri, word_regex, ignore_word_regex):
             if uri_word in uri_ignore_words:
-                check_words.remove(uri_word)
+                # determine/remove only the first among matches
+                for i, match in enumerate(check_matches):
+                    if match.group() == uri_word:
+                        check_matches = check_matches[:i] + check_matches[i + 1 :]
+                        break
+    return check_matches
 
 
 def parse_file(
@@ -855,18 +883,18 @@ def parse_file(
         # outside, it will still be a spelling error.
         if "*" in uri_ignore_words:
             line = uri_regex.sub(" ", line)
-        check_words = extract_words(line, word_regex, ignore_word_regex)
+        check_matches = extract_words_iter(line, word_regex, ignore_word_regex)
         if "*" not in uri_ignore_words:
-            apply_uri_ignore_words(
-                check_words,
+            check_matches = apply_uri_ignore_words(
+                check_matches,
                 line,
                 word_regex,
                 ignore_word_regex,
                 uri_regex,
                 uri_ignore_words,
             )
-
-        for word in check_words:
+        for match in check_matches:
+            word = match.group()
             lword = word.lower()
             if lword in misspellings:
                 context_shown = False
@@ -878,7 +906,11 @@ def parse_file(
                         context_shown = True
                         print_context(lines, i, context)
                     fix, fixword = ask_for_word_fix(
-                        lines[i], word, misspellings[lword], options.interactive
+                        lines[i],
+                        match,
+                        misspellings[lword],
+                        options.interactive,
+                        colors=colors,
                     )
                     asked_for.add(lword)