From 1a1c8fb4433e4b938e7a12f6aa05e9c71823adf4 Mon Sep 17 00:00:00 2001
From: Stefan Behnel <stefan_ml@behnel.de>
Date: Thu, 31 Aug 2017 22:43:45 +0200
Subject: [PATCH] Avoid f-string formatting of known unicode strings also for
"!s" conversion. Evaluate and join more f-string constants at compile time,
including unprefixed strings. Fix a case where f-string constants could have
incorrect constant compile time result values, thus leading to incorrect
comparisons and constant folding errors.
---
CHANGES.rst | 3 +++
Cython/Compiler/ExprNodes.py | 2 +-
Cython/Compiler/Optimize.py | 21 +++++++++++++++++----
tests/run/fstring.pyx | 28 ++++++++++++++++++++++++++++
4 files changed, 49 insertions(+), 5 deletions(-)
diff --git a/CHANGES.rst b/CHANGES.rst
index bdf8c845b..c4e3043a3 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -50,6 +50,9 @@ Bugs fixed
* abs(signed int) now returns a signed rather than unsigned int.
(Github issue #1837)
+* Compile time evaluations of (partially) constant f-strings could show incorrect
+ results.
+
Other changes
-------------
diff --git a/Cython/Compiler/ExprNodes.py b/Cython/Compiler/ExprNodes.py
index f0ea3f980..f2dcdbbc0 100644
--- a/Cython/Compiler/ExprNodes.py
+++ b/Cython/Compiler/ExprNodes.py
@@ -3126,7 +3126,7 @@ class FormattedValueNode(ExprNode):
self.format_spec = self.format_spec.analyse_types(env).coerce_to_pyobject(env)
if self.c_format_spec is None:
self.value = self.value.coerce_to_pyobject(env)
- if not self.format_spec and not self.conversion_char:
+ if not self.format_spec and (not self.conversion_char or self.conversion_char == 's'):
if self.value.type is unicode_type and not self.value.may_be_none():
# value is definitely a unicode string and we don't format it any special
return self.value
diff --git a/Cython/Compiler/Optimize.py b/Cython/Compiler/Optimize.py
index 109c49794..479165f74 100644
--- a/Cython/Compiler/Optimize.py
+++ b/Cython/Compiler/Optimize.py
@@ -3959,10 +3959,21 @@ class ConstantFolding(Visitor.VisitorTransform, SkipDeclarations):
def visit_FormattedValueNode(self, node):
self.visitchildren(node)
+ conversion_char = node.conversion_char or 's'
if isinstance(node.format_spec, ExprNodes.UnicodeNode) and not node.format_spec.value:
node.format_spec = None
- if node.format_spec is None and node.conversion_char is None and isinstance(node.value, ExprNodes.UnicodeNode):
- return node.value
+ if node.format_spec is None and isinstance(node.value, ExprNodes.IntNode):
+ value = EncodedString(node.value.value)
+ if value.isdigit():
+ return ExprNodes.UnicodeNode(node.value.pos, value=value, constant_result=value)
+ if node.format_spec is None and conversion_char == 's':
+ value = None
+ if isinstance(node.value, ExprNodes.UnicodeNode):
+ value = node.value.value
+ elif isinstance(node.value, ExprNodes.StringNode):
+ value = node.value.unicode_value
+ if value is not None:
+ return ExprNodes.UnicodeNode(node.value.pos, value=value, constant_result=value)
return node
def visit_JoinedStrNode(self, node):
@@ -3980,7 +3991,8 @@ class ConstantFolding(Visitor.VisitorTransform, SkipDeclarations):
substrings = list(substrings)
unode = substrings[0]
if len(substrings) > 1:
- unode.value = EncodedString(u''.join(value.value for value in substrings))
+ value = EncodedString(u''.join(value.value for value in substrings))
+ unode = ExprNodes.UnicodeNode(unode.pos, value=value, constant_result=value)
# ignore empty Unicode strings
if unode.value:
values.append(unode)
@@ -3988,7 +4000,8 @@ class ConstantFolding(Visitor.VisitorTransform, SkipDeclarations):
values.extend(substrings)
if not values:
- node = ExprNodes.UnicodeNode(node.pos, value=EncodedString(''))
+ value = EncodedString('')
+ node = ExprNodes.UnicodeNode(node.pos, value=value, constant_result=value)
elif len(values) == 1:
node = values[0]
elif len(values) == 2:
diff --git a/tests/run/fstring.pyx b/tests/run/fstring.pyx
index b01662f91..09f5ec496 100644
--- a/tests/run/fstring.pyx
+++ b/tests/run/fstring.pyx
@@ -5,6 +5,8 @@
# Cython specific PEP 498 tests in addition to test_fstring.pyx from CPython
####
+cimport cython
+
import sys
IS_PYPY = hasattr(sys, 'pypy_version_info')
@@ -18,13 +20,39 @@ max_long = LONG_MAX
min_long = LONG_MIN
+@cython.test_fail_if_path_exists(
+ "//FormattedValueNode",
+ "//JoinedStrNode",
+ "//AddNode",
+)
def escaping():
"""
>>> escaping()
"""
assert f'{{{{{"abc"}}}}}{{}}{{' == '{{abc}}{}{'
+ s = f'{{{{{"abc"}}}}}{{}}{{'
+ assert s == '{{abc}}{}{', s
+
assert f'\x7b}}' == '{}'
+ s = f'\x7b}}'
+ assert s == '{}', s
+
assert f'{"{{}}"}' == '{{}}'
+ s = f'{"{{}}"}'
+ assert s == '{{}}', s
+
+
+@cython.test_fail_if_path_exists(
+ "//FormattedValueNode",
+ "//JoinedStrNode",
+ "//AddNode",
+)
+def nested_constant():
+ """
+ >>> nested_constant()
+ 'xyabc123321'
+ """
+ return f"""{f'''xy{f"abc{123}{'321'}"!s}'''}"""
def format2(ab, cd):
--
2.30.9