From ccc4ce28cc9077d77a0bc9e72b1177eba1be7186 Mon Sep 17 00:00:00 2001
From: Jon Turney <jon.turney@dronecode.org.uk>
Date: Sun, 28 Apr 2019 21:06:36 +0100
Subject: [PATCH] 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
---
 docs/markdown/Syntax.md                            |  3 +++
 mesonbuild/mparser.py                              | 12 ++++++------
 .../common/185 escape and unicode/meson.build      | 14 ++++++++++++++
 3 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/docs/markdown/Syntax.md b/docs/markdown/Syntax.md
index cf56dd3f4..aadb14afe 100644
--- a/docs/markdown/Syntax.md
+++ b/docs/markdown/Syntax.md
@@ -116,6 +116,9 @@ The full list of escape sequences is:
 
 As in python and C, up to three octal digits are accepted in `\ooo`.
 
+Unrecognized escape sequences are left in the string unchanged, i.e., the
+backslash is left in the string.
+
 #### String concatenation
 
 Strings can be concatenated to form a new string using the `+` symbol.
diff --git a/mesonbuild/mparser.py b/mesonbuild/mparser.py
index 17783ce2d..4305a7cb4 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):
diff --git a/test cases/common/185 escape and unicode/meson.build b/test cases/common/185 escape and unicode/meson.build
index 65377b6a3..e4fe628ae 100644
--- a/test cases/common/185 escape and unicode/meson.build	
+++ b/test cases/common/185 escape and unicode/meson.build	
@@ -22,3 +22,17 @@ foreach l : find_file_list.stdout().strip('\x00').split('\x00')
 endforeach
 
 test('second', executable('second', found_files_hex + [gen_file]))
+
+# Unrecognized and malformed escape sequences are literal
+
+malformed = [
+ [ '\c', 'c' ],
+ [ '\Uabcdefghi', 'Uabcdefghi'],
+ [ '\u123 ', 'u123 '],
+ [ '\xqr', 'xqr'],
+]
+
+foreach m : malformed
+  assert(m[0].endswith(m[1]), 'bad escape sequence had unexpected end')
+  assert(m[0].startswith('\\'), 'bad escape sequence had unexpected start')
+endforeach