kastiglione created this revision.
kastiglione added reviewers: JDevlieghere, jingham, mib, aprantl.
Herald added a subscriber: mgorny.
Herald added a project: All.
kastiglione requested review of this revision.
Herald added a project: LLDB.
Herald added a subscriber: lldb-commits.
Use `std::regex` as the backing implementation of `RegularExpression`.
This provides common and expected regex features, from basic features like
`\w` and `\d` character classes, to more advanced features such as lookahead.
This change used to be gated on the minimum GCC version, because some versions
of GCC had incomplete support for `std::regex`, but the GCC required by llvm
for the past couple years should be sufficient, according to docs. At this time
GCC >=7.1 is required.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D132307
Files:
lldb/include/lldb/Utility/RegularExpression.h
lldb/source/Utility/CMakeLists.txt
lldb/source/Utility/RegularExpression.cpp
lldb/test/API/commands/breakpoint/set/func-regex/TestBreakpointRegexError.py
lldb/test/API/functionalities/breakpoint/source_regexp/TestSourceRegexBreakpoints.py
lldb/test/API/functionalities/breakpoint/source_regexp/a.c
lldb/test/API/functionalities/breakpoint/source_regexp/main.c
lldb/test/API/functionalities/data-formatter/data-formatter-stl/generic/multiset/TestDataFormatterGenericMultiSet.py
lldb/test/API/functionalities/data-formatter/data-formatter-stl/generic/set/TestDataFormatterGenericSet.py
Index: lldb/test/API/functionalities/data-formatter/data-formatter-stl/generic/set/TestDataFormatterGenericSet.py
===================================================================
--- lldb/test/API/functionalities/data-formatter/data-formatter-stl/generic/set/TestDataFormatterGenericSet.py
+++ lldb/test/API/functionalities/data-formatter/data-formatter-stl/generic/set/TestDataFormatterGenericSet.py
@@ -130,7 +130,7 @@
"""Test that the data formatters work on ref and ptr."""
self.build()
(self.target, process, _, bkpt) = lldbutil.run_to_source_breakpoint(
- self, "Stop here to check by ref and ptr.",
+ self, "Stop here to check by ref and ptr",
lldb.SBFileSpec("main.cpp", False))
# The reference should print just like the value:
self.check("ref", 7)
Index: lldb/test/API/functionalities/data-formatter/data-formatter-stl/generic/multiset/TestDataFormatterGenericMultiSet.py
===================================================================
--- lldb/test/API/functionalities/data-formatter/data-formatter-stl/generic/multiset/TestDataFormatterGenericMultiSet.py
+++ lldb/test/API/functionalities/data-formatter/data-formatter-stl/generic/multiset/TestDataFormatterGenericMultiSet.py
@@ -129,7 +129,7 @@
"""Test that the data formatters work on ref and ptr."""
self.build(dictionary={stdlib_type: "1"})
(self.target, process, _, bkpt) = lldbutil.run_to_source_breakpoint(
- self, "Stop here to check by ref and ptr.",
+ self, "Stop here to check by ref and ptr",
lldb.SBFileSpec("main.cpp", False))
# The reference should print just like the value:
self.check("ref", 7)
Index: lldb/test/API/functionalities/breakpoint/source_regexp/main.c
===================================================================
--- lldb/test/API/functionalities/breakpoint/source_regexp/main.c
+++ lldb/test/API/functionalities/breakpoint/source_regexp/main.c
@@ -4,7 +4,7 @@
int
main_func(int input)
{
- return printf("Set B breakpoint here: %d.\n", input);
+ return printf("Set B0 breakpoint here: %d.\n", input);
}
int
Index: lldb/test/API/functionalities/breakpoint/source_regexp/a.c
===================================================================
--- lldb/test/API/functionalities/breakpoint/source_regexp/a.c
+++ lldb/test/API/functionalities/breakpoint/source_regexp/a.c
@@ -5,12 +5,12 @@
static int
main_func(int input)
{
- return printf("Set B breakpoint here: %d", input);
+ return printf("Set B2 breakpoint here: %d", input);
}
int
a_func(int input)
{
- input += 1; // Set A breakpoint here;
+ input += 1; // Set A1 breakpoint here;
return main_func(input);
}
Index: lldb/test/API/functionalities/breakpoint/source_regexp/TestSourceRegexBreakpoints.py
===================================================================
--- lldb/test/API/functionalities/breakpoint/source_regexp/TestSourceRegexBreakpoints.py
+++ lldb/test/API/functionalities/breakpoint/source_regexp/TestSourceRegexBreakpoints.py
@@ -34,7 +34,7 @@
func_names = lldb.SBStringList()
func_names.AppendString("a_func")
- source_regex = "Set . breakpoint here"
+ source_regex = r"Set \w\d? breakpoint here"
main_break = target.BreakpointCreateBySourceRegex(
source_regex, lldb.SBFileSpecList(), target_files, func_names)
num_locations = main_break.GetNumLocations()
@@ -50,7 +50,7 @@
address.IsValid(),
"Got a valid address from the location.")
- a_func_line = line_number("a.c", "Set A breakpoint here")
+ a_func_line = line_number("a.c", "Set A1 breakpoint here")
line_entry = address.GetLineEntry()
self.assertTrue(line_entry.IsValid(), "Got a valid line entry.")
self.assertEquals(line_entry.line, a_func_line,
@@ -66,7 +66,7 @@
# First look just in main:
target_files = lldb.SBFileSpecList()
target_files.Append(lldb.SBFileSpec("main.c"))
- source_regex = "Set . breakpoint here"
+ source_regex = r"Set \w\d? breakpoint here"
main_break = target.BreakpointCreateBySourceRegex(
source_regex, lldb.SBFileSpecList(), target_files, lldb.SBStringList())
Index: lldb/test/API/commands/breakpoint/set/func-regex/TestBreakpointRegexError.py
===================================================================
--- lldb/test/API/commands/breakpoint/set/func-regex/TestBreakpointRegexError.py
+++ lldb/test/API/commands/breakpoint/set/func-regex/TestBreakpointRegexError.py
@@ -8,17 +8,17 @@
@no_debug_info_test
def test_error(self):
self.expect("breakpoint set --func-regex (", error=True,
- substrs=["error: Function name regular expression could " +
- "not be compiled: parentheses not balanced"])
+ substrs=["error: Function name regular expression could "
+ "not be compiled: The expression contained mismatched ( and )."])
# Point out if looks like the user provided a globbing expression.
self.expect("breakpoint set --func-regex *a", error=True,
- substrs=["error: Function name regular expression could " +
- "not be compiled: repetition-operator operand invalid",
+ substrs=["error: Function name regular expression could "
+ "not be compiled: One of *?+{ was not preceded by a valid regular expression.",
"warning: Function name regex does not accept glob patterns."])
self.expect("breakpoint set --func-regex ?a", error=True,
- substrs=["error: Function name regular expression could " +
- "not be compiled: repetition-operator operand invalid",
+ substrs=["error: Function name regular expression could "
+ "not be compiled: One of *?+{ was not preceded by a valid regular expression.",
"warning: Function name regex does not accept glob patterns."])
# Make sure that warning is only shown for invalid regular expressions
# that look like a globbing expression (i.e., they have a leading * or ?).
Index: lldb/source/Utility/RegularExpression.cpp
===================================================================
--- lldb/source/Utility/RegularExpression.cpp
+++ lldb/source/Utility/RegularExpression.cpp
@@ -7,15 +7,21 @@
//===----------------------------------------------------------------------===//
#include "lldb/Utility/RegularExpression.h"
+#include "llvm/ADT/StringRef.h"
#include <string>
using namespace lldb_private;
RegularExpression::RegularExpression(llvm::StringRef str)
- : m_regex_text(std::string(str)),
- // m_regex does not reference str anymore after it is constructed.
- m_regex(llvm::Regex(str)) {}
+ // m_regex does not reference str anymore after it is constructed.
+ : m_regex_text(std::string(str)) {
+ try {
+ m_regex = m_regex_text;
+ } catch (const std::regex_error &e) {
+ m_regex_error = e;
+ }
+}
RegularExpression::RegularExpression(const RegularExpression &rhs)
: RegularExpression(rhs.GetText()) {}
@@ -25,17 +31,33 @@
llvm::SmallVectorImpl<llvm::StringRef> *matches) const {
if (!IsValid())
return false;
- return m_regex.match(str, matches);
+
+ if (!matches)
+ return std::regex_search(str.begin(), str.end(), m_regex);
+
+ std::cmatch result;
+ if (!std::regex_search(str.begin(), str.end(), result, m_regex))
+ return false;
+
+ matches->clear();
+ for (const auto &sub : result) {
+ llvm::StringRef match(sub.first, sub.length());
+ matches->push_back(match);
+ }
+ return true;
}
-bool RegularExpression::IsValid() const { return m_regex.isValid(); }
+bool RegularExpression::IsValid() const {
+ return !m_regex_text.empty() && !m_regex_error;
+}
llvm::StringRef RegularExpression::GetText() const { return m_regex_text; }
llvm::Error RegularExpression::GetError() const {
- std::string error;
- if (!m_regex.isValid(error))
+ if (!IsValid()) {
+ std::string error = m_regex_error ? m_regex_error->what() : "empty regex";
return llvm::make_error<llvm::StringError>(error,
llvm::inconvertibleErrorCode());
+ }
return llvm::Error::success();
}
Index: lldb/source/Utility/CMakeLists.txt
===================================================================
--- lldb/source/Utility/CMakeLists.txt
+++ lldb/source/Utility/CMakeLists.txt
@@ -23,6 +23,12 @@
list(APPEND LLDB_SYSTEM_LIBS atomic)
endif()
+set_source_files_properties(
+ RegularExpression.cpp
+ PROPERTIES COMPILE_OPTIONS
+ "-fcxx-exceptions"
+)
+
add_lldb_library(lldbUtility
ArchSpec.cpp
Args.cpp
Index: lldb/include/lldb/Utility/RegularExpression.h
===================================================================
--- lldb/include/lldb/Utility/RegularExpression.h
+++ lldb/include/lldb/Utility/RegularExpression.h
@@ -13,6 +13,8 @@
#include "llvm/Support/Error.h"
#include "llvm/Support/Regex.h"
+#include <optional>
+#include <regex>
namespace lldb_private {
class RegularExpression {
@@ -86,7 +88,8 @@
/// A copy of the original regular expression text.
std::string m_regex_text;
/// The compiled regular expression.
- mutable llvm::Regex m_regex;
+ std::regex m_regex;
+ std::optional<std::regex_error> m_regex_error;
};
} // namespace lldb_private
_______________________________________________
lldb-commits mailing list
lldb-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/lldb-commits
