]> git.madduck.net Git - etc/vim.git/commitdiff

madduck's git repository

Every one of the projects in this repository is available at the canonical URL git://git.madduck.net/madduck/pub/<projectpath> — see each project's metadata for the exact URL.

All patches and comments are welcome. Please squash your changes to logical commits before using git-format-patch and git-send-email to patches@git.madduck.net. If you'd read over the Git project's submission guidelines and adhered to them, I'd be especially grateful.

SSH access, as well as push access can be individually arranged.

If you use my repositories frequently, consider adding the following snippet to ~/.gitconfig and using the third clone URL listed for each project:

[url "git://git.madduck.net/madduck/"]
  insteadOf = madduck:

Format hex code in unicode escape sequences in string literals (#2916)
authorShivansh-007 <shivansh-007@outlook.com>
Sun, 22 Jan 2023 13:21:09 +0000 (18:51 +0530)
committerGitHub <noreply@github.com>
Sun, 22 Jan 2023 13:21:09 +0000 (05:21 -0800)
Co-authored-by: Jelle Zijlstra <jelle.zijlstra@gmail.com>
CHANGES.md
src/black/linegen.py
src/black/mode.py
src/black/strings.py
tests/data/preview/format_unicode_escape_seq.py [new file with mode: 0644]

index 1450278341b8eac4d6380ac59f1f74d32ee0f413..e2e4b341761eb679b21d8fbb990946bbac304c81 100644 (file)
@@ -16,6 +16,7 @@
 
 <!-- Changes that affect Black's preview style -->
 
 
 <!-- Changes that affect Black's preview style -->
 
+- Format hex code in unicode escape sequences in string literals (#2916)
 - Add parentheses around `if`-`else` expressions (#2278)
 - Improve the performance on large expressions that contain many strings (#3467)
 - Fix a crash in preview style with assert + parenthesized string (#3415)
 - Add parentheses around `if`-`else` expressions (#2278)
 - Improve the performance on large expressions that contain many strings (#3467)
 - Fix a crash in preview style with assert + parenthesized string (#3415)
index 2f50257a9305b0203ee662e4d5d3187bbe20741d..bfc28ca006ccc44d72185a2cd355c7e958d31de6 100644 (file)
@@ -59,6 +59,7 @@ from black.strings import (
     get_string_prefix,
     normalize_string_prefix,
     normalize_string_quotes,
     get_string_prefix,
     normalize_string_prefix,
     normalize_string_quotes,
+    normalize_unicode_escape_sequences,
 )
 from black.trans import (
     CannotTransform,
 )
 from black.trans import (
     CannotTransform,
@@ -368,6 +369,9 @@ class LineGenerator(Visitor[Line]):
         yield from self.visit_default(node)
 
     def visit_STRING(self, leaf: Leaf) -> Iterator[Line]:
         yield from self.visit_default(node)
 
     def visit_STRING(self, leaf: Leaf) -> Iterator[Line]:
+        if Preview.hex_codes_in_unicode_sequences in self.mode:
+            normalize_unicode_escape_sequences(leaf)
+
         if is_docstring(leaf) and "\\\n" not in leaf.value:
             # We're ignoring docstrings with backslash newline escapes because changing
             # indentation of those changes the AST representation of the code.
         if is_docstring(leaf) and "\\\n" not in leaf.value:
             # We're ignoring docstrings with backslash newline escapes because changing
             # indentation of those changes the AST representation of the code.
index af0706e6a0b2a425b1c312625b2657867eae4e46..4309d4fa635b784d5f0eb5d438fd185957383457 100644 (file)
@@ -153,6 +153,7 @@ def supports_feature(target_versions: Set[TargetVersion], feature: Feature) -> b
 class Preview(Enum):
     """Individual preview style features."""
 
 class Preview(Enum):
     """Individual preview style features."""
 
+    hex_codes_in_unicode_sequences = auto()
     annotation_parens = auto()
     empty_lines_before_class_or_def_with_leading_comments = auto()
     handle_trailing_commas_in_head = auto()
     annotation_parens = auto()
     empty_lines_before_class_or_def_with_leading_comments = auto()
     handle_trailing_commas_in_head = auto()
index 9d0e2eb8430e538efcba96582dcfc9ee2d4bc468..3e3bc12fe728cd4a23f3b19395506e88b109723c 100644 (file)
@@ -5,7 +5,9 @@ Simple formatting on strings. Further string formatting code is in trans.py.
 import re
 import sys
 from functools import lru_cache
 import re
 import sys
 from functools import lru_cache
-from typing import List, Pattern
+from typing import List, Match, Pattern
+
+from blib2to3.pytree import Leaf
 
 if sys.version_info < (3, 8):
     from typing_extensions import Final
 
 if sys.version_info < (3, 8):
     from typing_extensions import Final
@@ -18,6 +20,15 @@ STRING_PREFIX_RE: Final = re.compile(
     r"^([" + STRING_PREFIX_CHARS + r"]*)(.*)$", re.DOTALL
 )
 FIRST_NON_WHITESPACE_RE: Final = re.compile(r"\s*\t+\s*(\S)")
     r"^([" + STRING_PREFIX_CHARS + r"]*)(.*)$", re.DOTALL
 )
 FIRST_NON_WHITESPACE_RE: Final = re.compile(r"\s*\t+\s*(\S)")
+UNICODE_ESCAPE_RE: Final = re.compile(
+    r"(?P<backslashes>\\+)(?P<body>"
+    r"(u(?P<u>[a-fA-F0-9]{4}))"  # Character with 16-bit hex value xxxx
+    r"|(U(?P<U>[a-fA-F0-9]{8}))"  # Character with 32-bit hex value xxxxxxxx
+    r"|(x(?P<x>[a-fA-F0-9]{2}))"  # Character with hex value hh
+    r"|(N\{(?P<N>[a-zA-Z0-9 \-]{2,})\})"  # Character named name in the Unicode database
+    r")",
+    re.VERBOSE,
+)
 
 
 def sub_twice(regex: Pattern[str], replacement: str, original: str) -> str:
 
 
 def sub_twice(regex: Pattern[str], replacement: str, original: str) -> str:
@@ -236,3 +247,34 @@ def normalize_string_quotes(s: str) -> str:
         return s  # Prefer double quotes
 
     return f"{prefix}{new_quote}{new_body}{new_quote}"
         return s  # Prefer double quotes
 
     return f"{prefix}{new_quote}{new_body}{new_quote}"
+
+
+def normalize_unicode_escape_sequences(leaf: Leaf) -> None:
+    """Replace hex codes in Unicode escape sequences with lowercase representation."""
+    text = leaf.value
+    prefix = get_string_prefix(text)
+    if "r" in prefix.lower():
+        return
+
+    def replace(m: Match[str]) -> str:
+        groups = m.groupdict()
+        back_slashes = groups["backslashes"]
+
+        if len(back_slashes) % 2 == 0:
+            return back_slashes + groups["body"]
+
+        if groups["u"]:
+            # \u
+            return back_slashes + "u" + groups["u"].lower()
+        elif groups["U"]:
+            # \U
+            return back_slashes + "U" + groups["U"].lower()
+        elif groups["x"]:
+            # \x
+            return back_slashes + "x" + groups["x"].lower()
+        else:
+            assert groups["N"], f"Unexpected match: {m}"
+            # \N{}
+            return back_slashes + "N{" + groups["N"].upper() + "}"
+
+    leaf.value = re.sub(UNICODE_ESCAPE_RE, replace, text)
diff --git a/tests/data/preview/format_unicode_escape_seq.py b/tests/data/preview/format_unicode_escape_seq.py
new file mode 100644 (file)
index 0000000..3440696
--- /dev/null
@@ -0,0 +1,33 @@
+x = "\x1F"
+x = "\\x1B"
+x = "\\\x1B"
+x = "\U0001F60E"
+x = "\u0001F60E"
+x = r"\u0001F60E"
+x = "don't format me"
+x = "\xA3"
+x = "\u2717"
+x = "\uFaCe"
+x = "\N{ox}\N{OX}"
+x = "\N{lAtIn smaLL letteR x}"
+x = "\N{CYRILLIC small LETTER BYELORUSSIAN-UKRAINIAN I}"
+x = b"\x1Fdon't byte"
+x = rb"\x1Fdon't format"
+
+# output
+
+x = "\x1f"
+x = "\\x1B"
+x = "\\\x1b"
+x = "\U0001f60e"
+x = "\u0001F60E"
+x = r"\u0001F60E"
+x = "don't format me"
+x = "\xa3"
+x = "\u2717"
+x = "\uface"
+x = "\N{OX}\N{OX}"
+x = "\N{LATIN SMALL LETTER X}"
+x = "\N{CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I}"
+x = b"\x1fdon't byte"
+x = rb"\x1Fdon't format"