consistent invalid escape sequence behaviour

* docs: document unrecognized escape sequence behaviour [skip ci]

Document that unrecognized escape sequence behaviour is like python, not
C.

* Don't try to decode invalid hex escape sequences

Don't try to decode escape sequences which should contain a sequence of
hex digits, but don't, throwing a python exception.  These will treated
literally instead.

* Extend test case to cover invalid escape sequences

1 files changed, 6 insertions, 6 deletions

diff --git a/mesonbuild/mparser.py b/mesonbuild/mparser.py
index 17783ce..4305a7c 100644
--- a/mesonbuild/mparser.py
+++ b/mesonbuild/mparser.py
@@ -21,12 +21,12 @@ from . import mlog
 # This is the regex for the supported escape sequences of a regular string
 # literal, like 'abc\x00'
 ESCAPE_SEQUENCE_SINGLE_RE = re.compile(r'''
-    ( \\U........      # 8-digit hex escapes
-    | \\u....          # 4-digit hex escapes
-    | \\x..            # 2-digit hex escapes
-    | \\[0-7]{1,3}     # Octal escapes
-    | \\N\{[^}]+\}     # Unicode characters by name
-    | \\[\\'abfnrtv]   # Single-character escapes
+    ( \\U[A-Fa-f0-9]{8}   # 8-digit hex escapes
+    | \\u[A-Fa-f0-9]{4}   # 4-digit hex escapes
+    | \\x[A-Fa-f0-9]{2}   # 2-digit hex escapes
+    | \\[0-7]{1,3}        # Octal escapes
+    | \\N\{[^}]+\}        # Unicode characters by name
+    | \\[\\'abfnrtv]      # Single-character escapes
     )''', re.UNICODE | re.VERBOSE)
 
 class MesonUnicodeDecodeError(MesonException):