From 7c3df9c23f25e0a516ac2856962a1d13538ef8e6 Mon Sep 17 00:00:00 2001
From: Cornelius Roemer <cornelius.roemer@gmail.com>
Date: Sun, 18 Aug 2024 19:39:43 +0200
Subject: [PATCH] feat: report file name of file that chardet fails to read

resolves #3519

Tested and it works now, reporting the file name:

```
codespell --write-changes -i3 -C 5 -H -f -e --count -s --builtin clear,rare,names
Failed to decode file ./pep_sphinx_extensions/tests/pep_lint/test_pep_number.py using detected encoding Windows-1254.
Traceback (most recent call last):
  File "/Users/corneliusromer/micromamba/envs/codespell/bin/codespell", line 8, in <module>
    sys.exit(_script_main())
             ^^^^^^^^^^^^^^
  File "/Users/corneliusromer/code/codespell/codespell_lib/_codespell.py", line 1103, in _script_main
    return main(*sys.argv[1:])
           ^^^^^^^^^^^^^^^^^^^
  File "/Users/corneliusromer/code/codespell/codespell_lib/_codespell.py", line 1300, in main
    bad_count += parse_file(
                 ^^^^^^^^^^^
  File "/Users/corneliusromer/code/codespell/codespell_lib/_codespell.py", line 945, in parse_file
    lines, encoding = file_opener.open(filename)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/corneliusromer/code/codespell/codespell_lib/_codespell.py", line 232, in open
    return self.open_with_chardet(filename)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/corneliusromer/code/codespell/codespell_lib/_codespell.py", line 246, in open_with_chardet
    lines = self.get_lines(f)
            ^^^^^^^^^^^^^^^^^
  File "/Users/corneliusromer/code/codespell/codespell_lib/_codespell.py", line 303, in get_lines
    lines = f.readlines()
            ^^^^^^^^^^^^^
  File "/Users/corneliusromer/micromamba/envs/codespell/lib/python3.12/encodings/cp1254.py", line 23, in decode
    return codecs.charmap_decode(input,self.errors,decoding_table)[0]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
UnicodeDecodeError: 'charmap' codec can't decode byte 0x90 in position 1349: character maps to <undefined>
```
---
 codespell_lib/_codespell.py | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/codespell_lib/_codespell.py b/codespell_lib/_codespell.py
index c7cc63bcfe..32bd61ad69 100644
--- a/codespell_lib/_codespell.py
+++ b/codespell_lib/_codespell.py
@@ -227,12 +227,12 @@ def init_chardet(self) -> None:
 
         self.encdetector = UniversalDetector()
 
-    def open(self, filename: str) -> Tuple[List[str], str]:
+    def open(self, filename: str) -> Tuple[List[str], str | None]:
         if self.use_chardet:
             return self.open_with_chardet(filename)
         return self.open_with_internal(filename)
 
-    def open_with_chardet(self, filename: str) -> Tuple[List[str], str]:
+    def open_with_chardet(self, filename: str) -> Tuple[List[str], str | None]:
         self.encdetector.reset()
         with open(filename, "rb") as fb:
             for line in fb:
@@ -241,26 +241,30 @@ def open_with_chardet(self, filename: str) -> Tuple[List[str], str]:
                     break
         self.encdetector.close()
         encoding = self.encdetector.result["encoding"]
-
+        if not encoding:
+            print(
+                f"WARNING: Chardet failed to detect encoding for file {filename}.",
+                file=sys.stderr,
+            )
         try:
-            f = open(filename, encoding=encoding, newline="")
+            with open(filename, encoding=encoding, newline="") as f:
+                lines = self.get_lines(f)
         except UnicodeDecodeError:
-            print(f"ERROR: Could not detect encoding: {filename}", file=sys.stderr)
+            error_msg = (
+                f"Failed to decode file {filename} using detected "
+                f"encoding {encoding}."
+            )
+            print(error_msg, file=sys.stderr)
             raise
         except LookupError:
-            print(
-                f"ERROR: Don't know how to handle encoding {encoding}: {filename}",
-                file=sys.stderr,
-            )
+            error_msg = f"Unknown encoding {encoding} detected for file {filename}."
+            print(error_msg, file=sys.stderr)
             raise
-        else:
-            lines = self.get_lines(f)
-            f.close()
 
-        return lines, f.encoding
+        return lines, encoding
 
     def open_with_internal(self, filename: str) -> Tuple[List[str], str]:
-        encoding = None
+        encoding: str
         first_try = True
         for encoding in ("utf-8", "iso-8859-1"):
             if first_try:
@@ -887,10 +891,10 @@ def parse_file(
     bad_count = 0
     lines = None
     changed = False
+    encoding: str | None = "utf-8"
 
     if filename == "-":
         f = sys.stdin
-        encoding = "utf-8"
         lines = f.readlines()
     else:
         if options.check_filenames: