summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--.travis.yml61
-rw-r--r--BUILD124
-rw-r--r--CMakeLists.txt18
-rw-r--r--Makefile6
-rw-r--r--WORKSPACE9
-rwxr-xr-xkokoro/bazel.sh12
-rwxr-xr-xkokoro/cmake.sh2
-rw-r--r--kokoro/ubuntu-cmake.cfg1
-rwxr-xr-xkokoro/ubuntu-cmake.sh4
-rw-r--r--re2.pc2
-rw-r--r--re2/bitstate.cc21
-rw-r--r--re2/dfa.cc26
-rw-r--r--re2/nfa.cc31
-rw-r--r--re2/onepass.cc6
-rw-r--r--re2/parse.cc31
-rw-r--r--re2/prog.cc12
-rw-r--r--re2/re2.cc12
-rw-r--r--re2/testing/backtrack.cc21
-rw-r--r--re2/testing/exhaustive_tester.cc2
-rw-r--r--re2/testing/regexp_generator.cc10
-rw-r--r--re2/testing/tester.cc8
-rw-r--r--re2_test.bzl12
22 files changed, 240 insertions, 191 deletions
diff --git a/.travis.yml b/.travis.yml
index f89c96d..71561ea 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,6 +1,6 @@
language: cpp
sudo: false
-dist: trusty
+dist: xenial
script:
- make
- make test
@@ -76,37 +76,8 @@ matrix:
apt:
sources:
- ubuntu-toolchain-r-test
- - llvm-toolchain-precise-3.5
- packages:
- - clang-3.5
- env:
- - MATRIX_EVAL="CC=clang-3.5 CXX=clang++-3.5"
- - os: linux
- addons:
- apt:
- sources:
- - ubuntu-toolchain-r-test
- - llvm-toolchain-precise-3.6
- packages:
- - clang-3.6
- env:
- - MATRIX_EVAL="CC=clang-3.6 CXX=clang++-3.6"
- - os: linux
- addons:
- apt:
- sources:
- - ubuntu-toolchain-r-test
- - llvm-toolchain-precise-3.7
- packages:
- - clang-3.7
- env:
- - MATRIX_EVAL="CC=clang-3.7 CXX=clang++-3.7"
- - os: linux
- addons:
- apt:
- sources:
- - ubuntu-toolchain-r-test
- - llvm-toolchain-precise-3.8
+ - sourceline: 'deb https://apt.llvm.org/xenial/ llvm-toolchain-xenial-3.8 main'
+ key_url: 'https://apt.llvm.org/llvm-snapshot.gpg.key'
packages:
- clang-3.8
env:
@@ -116,7 +87,8 @@ matrix:
apt:
sources:
- ubuntu-toolchain-r-test
- - llvm-toolchain-precise-3.9
+ - sourceline: 'deb https://apt.llvm.org/xenial/ llvm-toolchain-xenial-3.9 main'
+ key_url: 'https://apt.llvm.org/llvm-snapshot.gpg.key'
packages:
- clang-3.9
env:
@@ -126,7 +98,8 @@ matrix:
apt:
sources:
- ubuntu-toolchain-r-test
- - llvm-toolchain-trusty-4.0
+ - sourceline: 'deb https://apt.llvm.org/xenial/ llvm-toolchain-xenial-4.0 main'
+ key_url: 'https://apt.llvm.org/llvm-snapshot.gpg.key'
packages:
- clang-4.0
env:
@@ -136,7 +109,8 @@ matrix:
apt:
sources:
- ubuntu-toolchain-r-test
- - llvm-toolchain-trusty-5.0
+ - sourceline: 'deb https://apt.llvm.org/xenial/ llvm-toolchain-xenial-5.0 main'
+ key_url: 'https://apt.llvm.org/llvm-snapshot.gpg.key'
packages:
- clang-5.0
env:
@@ -146,7 +120,7 @@ matrix:
apt:
sources:
- ubuntu-toolchain-r-test
- - sourceline: 'deb https://apt.llvm.org/trusty/ llvm-toolchain-trusty-6.0 main'
+ - sourceline: 'deb https://apt.llvm.org/xenial/ llvm-toolchain-xenial-6.0 main'
key_url: 'https://apt.llvm.org/llvm-snapshot.gpg.key'
packages:
- clang-6.0
@@ -157,7 +131,7 @@ matrix:
apt:
sources:
- ubuntu-toolchain-r-test
- - sourceline: 'deb https://apt.llvm.org/trusty/ llvm-toolchain-trusty-7 main'
+ - sourceline: 'deb https://apt.llvm.org/xenial/ llvm-toolchain-xenial-7 main'
key_url: 'https://apt.llvm.org/llvm-snapshot.gpg.key'
packages:
- clang-7
@@ -168,12 +142,23 @@ matrix:
apt:
sources:
- ubuntu-toolchain-r-test
- - sourceline: 'deb https://apt.llvm.org/trusty/ llvm-toolchain-trusty-8 main'
+ - sourceline: 'deb https://apt.llvm.org/xenial/ llvm-toolchain-xenial-8 main'
key_url: 'https://apt.llvm.org/llvm-snapshot.gpg.key'
packages:
- clang-8
env:
- MATRIX_EVAL="CC=clang-8 CXX=clang++-8"
+ - os: linux
+ addons:
+ apt:
+ sources:
+ - ubuntu-toolchain-r-test
+ - sourceline: 'deb https://apt.llvm.org/xenial/ llvm-toolchain-xenial-9 main'
+ key_url: 'https://apt.llvm.org/llvm-snapshot.gpg.key'
+ packages:
+ - clang-9
+ env:
+ - MATRIX_EVAL="CC=clang-9 CXX=clang++-9"
before_install:
- eval "${MATRIX_EVAL}"
diff --git a/BUILD b/BUILD
index 30ce320..f3191b9 100644
--- a/BUILD
+++ b/BUILD
@@ -23,6 +23,8 @@ config_setting(
values = {"cpu": "x64_windows_msvc"},
)
+load("@rules_cc//cc:defs.bzl", "cc_binary", "cc_library", "cc_test")
+
cc_library(
name = "re2",
srcs = [
@@ -122,106 +124,144 @@ cc_library(
deps = [":testing"],
)
-load(":re2_test.bzl", "re2_test")
-
-re2_test(
- "charclass_test",
+cc_test(
+ name = "charclass_test",
size = "small",
+ srcs = ["re2/testing/charclass_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "compile_test",
+cc_test(
+ name = "compile_test",
size = "small",
+ srcs = ["re2/testing/compile_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "filtered_re2_test",
+cc_test(
+ name = "filtered_re2_test",
size = "small",
+ srcs = ["re2/testing/filtered_re2_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "mimics_pcre_test",
+cc_test(
+ name = "mimics_pcre_test",
size = "small",
+ srcs = ["re2/testing/mimics_pcre_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "parse_test",
+cc_test(
+ name = "parse_test",
size = "small",
+ srcs = ["re2/testing/parse_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "possible_match_test",
+cc_test(
+ name = "possible_match_test",
size = "small",
+ srcs = ["re2/testing/possible_match_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "re2_arg_test",
+cc_test(
+ name = "re2_arg_test",
size = "small",
+ srcs = ["re2/testing/re2_arg_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "re2_test",
+cc_test(
+ name = "re2_test",
size = "small",
+ srcs = ["re2/testing/re2_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "regexp_test",
+cc_test(
+ name = "regexp_test",
size = "small",
+ srcs = ["re2/testing/regexp_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "required_prefix_test",
+cc_test(
+ name = "required_prefix_test",
size = "small",
+ srcs = ["re2/testing/required_prefix_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "search_test",
+cc_test(
+ name = "search_test",
size = "small",
+ srcs = ["re2/testing/search_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "set_test",
+cc_test(
+ name = "set_test",
size = "small",
+ srcs = ["re2/testing/set_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "simplify_test",
+cc_test(
+ name = "simplify_test",
size = "small",
+ srcs = ["re2/testing/simplify_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "string_generator_test",
+cc_test(
+ name = "string_generator_test",
size = "small",
+ srcs = ["re2/testing/string_generator_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "dfa_test",
+cc_test(
+ name = "dfa_test",
size = "large",
+ srcs = ["re2/testing/dfa_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "exhaustive1_test",
+cc_test(
+ name = "exhaustive1_test",
size = "large",
+ srcs = ["re2/testing/exhaustive1_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "exhaustive2_test",
+cc_test(
+ name = "exhaustive2_test",
size = "large",
+ srcs = ["re2/testing/exhaustive2_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "exhaustive3_test",
+cc_test(
+ name = "exhaustive3_test",
size = "large",
+ srcs = ["re2/testing/exhaustive3_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "exhaustive_test",
+cc_test(
+ name = "exhaustive_test",
size = "large",
+ srcs = ["re2/testing/exhaustive_test.cc"],
+ deps = [":test"],
)
-re2_test(
- "random_test",
+cc_test(
+ name = "random_test",
size = "large",
+ srcs = ["re2/testing/random_test.cc"],
+ deps = [":test"],
)
cc_library(
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 639c715..5c980f0 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -2,8 +2,8 @@
# Use of this source code is governed by a BSD-style
# license that can be found in the LICENSE file.
-# Old enough to support Ubuntu Trusty.
-cmake_minimum_required(VERSION 2.8.12)
+# Old enough to support Ubuntu Xenial.
+cmake_minimum_required(VERSION 3.5.1)
if(POLICY CMP0048)
cmake_policy(SET CMP0048 NEW)
@@ -11,6 +11,7 @@ endif()
project(RE2 CXX)
include(CTest)
+include(GNUInstallDirs)
option(BUILD_SHARED_LIBS "build shared libraries" OFF)
option(USEPCRE "use PCRE in tests and benchmarks" OFF)
@@ -27,7 +28,6 @@ if(CMAKE_CXX_COMPILER_ID MATCHES "MSVC")
endif()
if(BUILD_SHARED_LIBS)
# See http://www.kitware.com/blog/home/post/939 for details.
- cmake_minimum_required(VERSION 3.4)
set(CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS ON)
endif()
# CMake defaults to /W3, but some users like /W4 (or /Wall) and /WX,
@@ -147,6 +147,12 @@ set(RE2_HEADERS
re2/stringpiece.h
)
-install(FILES ${RE2_HEADERS} DESTINATION include/re2)
-install(TARGETS re2 EXPORT re2Config ARCHIVE DESTINATION lib LIBRARY DESTINATION lib RUNTIME DESTINATION bin INCLUDES DESTINATION include)
-install(EXPORT re2Config DESTINATION lib/cmake/re2 NAMESPACE re2::)
+install(FILES ${RE2_HEADERS}
+ DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/re2)
+install(TARGETS re2 EXPORT re2Config
+ ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
+ LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
+ RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
+ INCLUDES DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
+install(EXPORT re2Config
+ DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/re2 NAMESPACE re2::)
diff --git a/Makefile b/Makefile
index f001f06..3571611 100644
--- a/Makefile
+++ b/Makefile
@@ -276,10 +276,8 @@ install: obj/libre2.a obj/so/libre2.$(SOEXT)
ln -sf libre2.$(SOEXTVER00) $(DESTDIR)$(libdir)/libre2.$(SOEXTVER)
ln -sf libre2.$(SOEXTVER00) $(DESTDIR)$(libdir)/libre2.$(SOEXT)
$(INSTALL_DATA) re2.pc $(DESTDIR)$(libdir)/pkgconfig/re2.pc
- $(SED_INPLACE) -e "s#@prefix@#${prefix}#" $(DESTDIR)$(libdir)/pkgconfig/re2.pc
- $(SED_INPLACE) -e "s#@exec_prefix@#${exec_prefix}#" $(DESTDIR)$(libdir)/pkgconfig/re2.pc
- $(SED_INPLACE) -e "s#@includedir@#${includedir}#" $(DESTDIR)$(libdir)/pkgconfig/re2.pc
- $(SED_INPLACE) -e "s#@libdir@#${libdir}#" $(DESTDIR)$(libdir)/pkgconfig/re2.pc
+ $(SED_INPLACE) -e "s#@includedir@#$(includedir)#" $(DESTDIR)$(libdir)/pkgconfig/re2.pc
+ $(SED_INPLACE) -e "s#@libdir@#$(libdir)#" $(DESTDIR)$(libdir)/pkgconfig/re2.pc
testinstall: static-testinstall shared-testinstall
@echo
diff --git a/WORKSPACE b/WORKSPACE
index de481fe..484abfe 100644
--- a/WORKSPACE
+++ b/WORKSPACE
@@ -3,4 +3,13 @@
# license that can be found in the LICENSE file.
# Bazel (http://bazel.io/) WORKSPACE file for RE2.
+
workspace(name = "com_googlesource_code_re2")
+
+load("@bazel_tools//tools/build_defs/repo:http.bzl", "http_archive")
+
+http_archive(
+ name = "rules_cc",
+ strip_prefix = "rules_cc-master",
+ urls = ["https://github.com/bazelbuild/rules_cc/archive/master.zip"],
+)
diff --git a/kokoro/bazel.sh b/kokoro/bazel.sh
index 95aee2e..75edc02 100755
--- a/kokoro/bazel.sh
+++ b/kokoro/bazel.sh
@@ -3,6 +3,18 @@ set -eux
cd git/re2
+case "${KOKORO_JOB_NAME}" in
+ */windows-*)
+ choco upgrade bazel -y -i
+ # Pin to Visual Studio 2015, which is the minimum that we support.
+ export BAZEL_VC='C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC'
+ ;;
+ *)
+ # Use the script provided by Kokoro.
+ use_bazel.sh latest
+ ;;
+esac
+
bazel clean
bazel build --compilation_mode=dbg -- //:all
bazel test --compilation_mode=dbg --test_output=errors -- //:all \
diff --git a/kokoro/cmake.sh b/kokoro/cmake.sh
index 999fbfe..7e355f8 100755
--- a/kokoro/cmake.sh
+++ b/kokoro/cmake.sh
@@ -5,6 +5,8 @@ cd git/re2
case "${KOKORO_JOB_NAME}" in
*/windows-*)
+ export PATH+=':/cygdrive/c/Program Files/CMake/bin'
+ # Pin to Visual Studio 2015, which is the minimum that we support.
CMAKE_G_A_FLAGS=('-G' 'Visual Studio 14 2015' '-A' 'x64')
;;
*)
diff --git a/kokoro/ubuntu-cmake.cfg b/kokoro/ubuntu-cmake.cfg
new file mode 100644
index 0000000..63d4f91
--- /dev/null
+++ b/kokoro/ubuntu-cmake.cfg
@@ -0,0 +1 @@
+build_file: "re2/kokoro/ubuntu-cmake.sh"
diff --git a/kokoro/ubuntu-cmake.sh b/kokoro/ubuntu-cmake.sh
new file mode 100755
index 0000000..ef4b7dc
--- /dev/null
+++ b/kokoro/ubuntu-cmake.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+set -eux
+bash git/re2/kokoro/cmake.sh
+exit $?
diff --git a/re2.pc b/re2.pc
index d66cf51..50fd637 100644
--- a/re2.pc
+++ b/re2.pc
@@ -1,5 +1,3 @@
-prefix=@prefix@
-exec_prefix=@exec_prefix@
includedir=@includedir@
libdir=@libdir@
diff --git a/re2/bitstate.cc b/re2/bitstate.cc
index 6f045b1..317b26f 100644
--- a/re2/bitstate.cc
+++ b/re2/bitstate.cc
@@ -86,7 +86,7 @@ BitState::BitState(Prog* prog)
// we don't repeat the visit.
bool BitState::ShouldVisit(int id, const char* p) {
int n = prog_->list_heads()[id] * static_cast<int>(text_.size()+1) +
- static_cast<int>(p-text_.begin());
+ static_cast<int>(p-text_.data());
if (visited_[n/VisitedBits] & (1 << (n & (VisitedBits-1))))
return false;
visited_[n/VisitedBits] |= 1 << (n & (VisitedBits-1));
@@ -134,7 +134,7 @@ void BitState::Push(int id, const char* p) {
// Return whether it succeeded.
bool BitState::TrySearch(int id0, const char* p0) {
bool matched = false;
- const char* end = text_.end();
+ const char* end = text_.data() + text_.size();
njob_ = 0;
// Push() no longer checks ShouldVisit(),
// so we must perform the check ourselves.
@@ -251,7 +251,7 @@ bool BitState::TrySearch(int id0, const char* p0) {
matched = true;
cap_[1] = p;
if (submatch_[0].data() == NULL ||
- (longest_ && p > submatch_[0].end())) {
+ (longest_ && p > submatch_[0].data() + submatch_[0].size())) {
for (int i = 0; i < nsubmatch_; i++)
submatch_[i] =
StringPiece(cap_[2 * i],
@@ -288,7 +288,7 @@ bool BitState::Search(const StringPiece& text, const StringPiece& context,
// Search parameters.
text_ = text;
context_ = context;
- if (context_.begin() == NULL)
+ if (context_.data() == NULL)
context_ = text;
if (prog_->anchor_start() && context_.begin() != text.begin())
return false;
@@ -319,8 +319,8 @@ bool BitState::Search(const StringPiece& text, const StringPiece& context,
// Anchored search must start at text.begin().
if (anchored_) {
- cap_[0] = text.begin();
- return TrySearch(prog_->start(), text.begin());
+ cap_[0] = text.data();
+ return TrySearch(prog_->start(), text.data());
}
// Unanchored search, starting from each possible text position.
@@ -329,13 +329,14 @@ bool BitState::Search(const StringPiece& text, const StringPiece& context,
// This looks like it's quadratic in the size of the text,
// but we are not clearing visited_ between calls to TrySearch,
// so no work is duplicated and it ends up still being linear.
- for (const char* p = text.begin(); p <= text.end(); p++) {
+ for (const char* p = text.data(); p <= text.data() + text.size(); p++) {
// Try to use memchr to find the first byte quickly.
int fb = prog_->first_byte();
- if (fb >= 0 && p < text.end() && (p[0] & 0xFF) != fb) {
- p = reinterpret_cast<const char*>(memchr(p, fb, text.end() - p));
+ if (fb >= 0 && p < text.data() + text.size() && (p[0] & 0xFF) != fb) {
+ p = reinterpret_cast<const char*>(
+ memchr(p, fb, text.data() + text.size() - p));
if (p == NULL)
- p = text.end();
+ p = text.data() + text.size();
}
cap_[0] = p;
diff --git a/re2/dfa.cc b/re2/dfa.cc
index 40880f9..f0d342a 100644
--- a/re2/dfa.cc
+++ b/re2/dfa.cc
@@ -1138,8 +1138,8 @@ DFA::RWLocker::RWLocker(Mutex* mu) : mu_(mu), writing_(false) {
mu_->ReaderLock();
}
-// This function is marked as NO_THREAD_SAFETY_ANALYSIS because the annotations
-// does not support lock upgrade.
+// This function is marked as NO_THREAD_SAFETY_ANALYSIS because
+// the annotations don't support lock upgrade.
void DFA::RWLocker::LockForWriting() NO_THREAD_SAFETY_ANALYSIS {
if (!writing_) {
mu_->ReaderUnlock();
@@ -1328,10 +1328,11 @@ inline bool DFA::InlinedSearchLoop(SearchParams* params,
bool want_earliest_match,
bool run_forward) {
State* start = params->start;
- const uint8_t* bp = BytePtr(params->text.begin()); // start of text
- const uint8_t* p = bp; // text scanning point
- const uint8_t* ep = BytePtr(params->text.end()); // end of text
- const uint8_t* resetp = NULL; // p at last cache reset
+ const uint8_t* bp = BytePtr(params->text.data()); // start of text
+ const uint8_t* p = bp; // text scanning point
+ const uint8_t* ep = BytePtr(params->text.data() +
+ params->text.size()); // end of text
+ const uint8_t* resetp = NULL; // p at last cache reset
if (!run_forward) {
using std::swap;
swap(p, ep);
@@ -1798,9 +1799,9 @@ bool DFA::Search(const StringPiece& text,
return false;
if (params.start == FullMatchState) {
if (run_forward == want_earliest_match)
- *epp = text.begin();
+ *epp = text.data();
else
- *epp = text.end();
+ *epp = text.data() + text.size();
return true;
}
if (ExtraDebug)
@@ -1863,7 +1864,7 @@ bool Prog::SearchDFA(const StringPiece& text, const StringPiece& const_context,
*failed = false;
StringPiece context = const_context;
- if (context.begin() == NULL)
+ if (context.data() == NULL)
context = text;
bool carat = anchor_start();
bool dollar = anchor_end();
@@ -1910,7 +1911,7 @@ bool Prog::SearchDFA(const StringPiece& text, const StringPiece& const_context,
return false;
if (!matched)
return false;
- if (endmatch && ep != (reversed_ ? text.begin() : text.end()))
+ if (endmatch && ep != (reversed_ ? text.data() : text.data() + text.size()))
return false;
// If caller cares, record the boundary of the match.
@@ -1918,10 +1919,11 @@ bool Prog::SearchDFA(const StringPiece& text, const StringPiece& const_context,
// as the beginning.
if (match0) {
if (reversed_)
- *match0 = StringPiece(ep, static_cast<size_t>(text.end() - ep));
+ *match0 =
+ StringPiece(ep, static_cast<size_t>(text.data() + text.size() - ep));
else
*match0 =
- StringPiece(text.begin(), static_cast<size_t>(ep - text.begin()));
+ StringPiece(text.data(), static_cast<size_t>(ep - text.data()));
}
return true;
}
diff --git a/re2/nfa.cc b/re2/nfa.cc
index 7bb4faf..e16831e 100644
--- a/re2/nfa.cc
+++ b/re2/nfa.cc
@@ -448,7 +448,7 @@ bool NFA::Search(const StringPiece& text, const StringPiece& const_context,
return false;
StringPiece context = const_context;
- if (context.begin() == NULL)
+ if (context.data() == NULL)
context = text;
// Sanity check: make sure that text lies within context.
@@ -465,7 +465,6 @@ bool NFA::Search(const StringPiece& text, const StringPiece& const_context,
if (prog_->anchor_end()) {
longest = true;
endmatch_ = true;
- etext_ = text.end();
}
if (nsubmatch < 0) {
@@ -488,7 +487,9 @@ bool NFA::Search(const StringPiece& text, const StringPiece& const_context,
matched_ = false;
// For debugging prints.
- btext_ = context.begin();
+ btext_ = context.data();
+ // For convenience.
+ etext_ = text.data() + text.size();
if (ExtraDebug)
fprintf(stderr, "NFA::Search %s (context: %s) anchored=%d longest=%d\n",
@@ -503,14 +504,14 @@ bool NFA::Search(const StringPiece& text, const StringPiece& const_context,
memset(&match_[0], 0, ncapture_*sizeof match_[0]);
// Loop over the text, stepping the machine.
- for (const char* p = text.begin();; p++) {
+ for (const char* p = text.data();; p++) {
if (ExtraDebug) {
int c = 0;
- if (p == context.begin())
+ if (p == btext_)
c = '^';
- else if (p > text.end())
+ else if (p > etext_)
c = '$';
- else if (p < text.end())
+ else if (p < etext_)
c = p[0] & 0xFF;
fprintf(stderr, "%c:", c);
@@ -524,14 +525,14 @@ bool NFA::Search(const StringPiece& text, const StringPiece& const_context,
}
// This is a no-op the first time around the loop because runq is empty.
- int id = Step(runq, nextq, p < text.end() ? p[0] & 0xFF : -1, context, p);
+ int id = Step(runq, nextq, p < etext_ ? p[0] & 0xFF : -1, context, p);
DCHECK_EQ(runq->size(), 0);
using std::swap;
swap(nextq, runq);
nextq->clear();
if (id != 0) {
// We're done: full match ahead.
- p = text.end();
+ p = etext_;
for (;;) {
Prog::Inst* ip = prog_->inst(id);
switch (ip->opcode()) {
@@ -559,30 +560,30 @@ bool NFA::Search(const StringPiece& text, const StringPiece& const_context,
break;
}
- if (p > text.end())
+ if (p > etext_)
break;
// Start a new thread if there have not been any matches.
// (No point in starting a new thread if there have been
// matches, since it would be to the right of the match
// we already found.)
- if (!matched_ && (!anchored || p == text.begin())) {
+ if (!matched_ && (!anchored || p == text.data())) {
// If there's a required first byte for an unanchored search
// and we're not in the middle of any possible matches,
// use memchr to search for the byte quickly.
int fb = prog_->first_byte();
if (!anchored && runq->size() == 0 &&
- fb >= 0 && p < text.end() && (p[0] & 0xFF) != fb) {
- p = reinterpret_cast<const char*>(memchr(p, fb, text.end() - p));
+ fb >= 0 && p < etext_ && (p[0] & 0xFF) != fb) {
+ p = reinterpret_cast<const char*>(memchr(p, fb, etext_ - p));
if (p == NULL) {
- p = text.end();
+ p = etext_;
}
}
Thread* t = AllocThread();
CopyCapture(t->capture, match_);
t->capture[0] = p;
- AddToThreadq(runq, start_, p < text.end() ? p[0] & 0xFF : -1, context, p,
+ AddToThreadq(runq, start_, p < etext_ ? p[0] & 0xFF : -1, context, p,
t);
Decref(t);
}
diff --git a/re2/onepass.cc b/re2/onepass.cc
index d615893..7a774ce 100644
--- a/re2/onepass.cc
+++ b/re2/onepass.cc
@@ -235,7 +235,7 @@ bool Prog::SearchOnePass(const StringPiece& text,
matchcap[i] = NULL;
StringPiece context = const_context;
- if (context.begin() == NULL)
+ if (context.data() == NULL)
context = text;
if (anchor_start() && context.begin() != text.begin())
return false;
@@ -249,8 +249,8 @@ bool Prog::SearchOnePass(const StringPiece& text,
// start() is always mapped to the zeroth OneState.
OneState* state = IndexToNode(nodes, statesize, 0);
uint8_t* bytemap = bytemap_;
- const char* bp = text.begin();
- const char* ep = text.end();
+ const char* bp = text.data();
+ const char* ep = text.data() + text.size();
const char* p;
bool matched = false;
matchcap[0] = bp;
diff --git a/re2/parse.cc b/re2/parse.cc
index 93b922a..03b53c7 100644
--- a/re2/parse.cc
+++ b/re2/parse.cc
@@ -1447,7 +1447,7 @@ static int UnHex(int c) {
// Sets *rp to the named character.
static bool ParseEscape(StringPiece* s, Rune* rp,
RegexpStatus* status, int rune_max) {
- const char* begin = s->begin();
+ const char* begin = s->data();
if (s->size() < 1 || (*s)[0] != '\\') {
// Should not happen - caller always checks.
status->set_code(kRegexpInternalError);
@@ -1590,7 +1590,7 @@ BadEscape:
// Unrecognized escape sequence.
status->set_code(kRegexpBadEscape);
status->set_error_arg(
- StringPiece(begin, static_cast<size_t>(s->begin() - begin)));
+ StringPiece(begin, static_cast<size_t>(s->data() - begin)));
return false;
}
@@ -1710,7 +1710,7 @@ const UGroup* MaybeParsePerlCCEscape(StringPiece* s, Regexp::ParseFlags parse_fl
return NULL;
// Could use StringPieceToRune, but there aren't
// any non-ASCII Perl group names.
- StringPiece name(s->begin(), 2);
+ StringPiece name(s->data(), 2);
const UGroup *g = LookupPerlGroup(name);
if (g == NULL)
return NULL;
@@ -1750,8 +1750,8 @@ ParseStatus ParseUnicodeGroup(StringPiece* s, Regexp::ParseFlags parse_flags,
return kParseError;
if (c != '{') {
// Name is the bit of string we just skipped over for c.
- const char* p = seq.begin() + 2;
- name = StringPiece(p, static_cast<size_t>(s->begin() - p));
+ const char* p = seq.data() + 2;
+ name = StringPiece(p, static_cast<size_t>(s->data() - p));
} else {
// Name is in braces. Look for closing }
size_t end = s->find('}', 0);
@@ -1762,14 +1762,14 @@ ParseStatus ParseUnicodeGroup(StringPiece* s, Regexp::ParseFlags parse_flags,
status->set_error_arg(seq);
return kParseError;
}
- name = StringPiece(s->begin(), end); // without '}'
+ name = StringPiece(s->data(), end); // without '}'
s->remove_prefix(end + 1); // with '}'
if (!IsValidUTF8(name, status))
return kParseError;
}
// Chop seq where s now begins.
- seq = StringPiece(seq.begin(), static_cast<size_t>(s->begin() - seq.begin()));
+ seq = StringPiece(seq.data(), static_cast<size_t>(s->data() - seq.data()));
if (name.size() > 0 && name[0] == '^') {
sign = -sign;
@@ -2074,8 +2074,8 @@ bool Regexp::ParseState::ParsePerlFlags(StringPiece* s) {
}
// t is "P<name>...", t[end] == '>'
- StringPiece capture(t.begin()-2, end+3); // "(?P<name>"
- StringPiece name(t.begin()+2, end-2); // "name"
+ StringPiece capture(t.data()-2, end+3); // "(?P<name>"
+ StringPiece name(t.data()+2, end-2); // "name"
if (!IsValidUTF8(name, status_))
return false;
if (!IsValidCaptureName(name)) {
@@ -2089,7 +2089,8 @@ bool Regexp::ParseState::ParsePerlFlags(StringPiece* s) {
return false;
}
- s->remove_prefix(static_cast<size_t>(capture.end() - s->begin()));
+ s->remove_prefix(
+ static_cast<size_t>(capture.data() + capture.size() - s->data()));
return true;
}
@@ -2173,7 +2174,7 @@ bool Regexp::ParseState::ParsePerlFlags(StringPiece* s) {
BadPerlOp:
status_->set_code(kRegexpBadPerlOp);
status_->set_error_arg(
- StringPiece(s->begin(), static_cast<size_t>(t.begin() - s->begin())));
+ StringPiece(s->data(), static_cast<size_t>(t.data() - s->data())));
return false;
}
@@ -2321,8 +2322,8 @@ Regexp* Regexp::Parse(const StringPiece& s, ParseFlags global_flags,
// (and a++ means something else entirely, which we don't support!)
status->set_code(kRegexpRepeatOp);
status->set_error_arg(StringPiece(
- lastunary.begin(),
- static_cast<size_t>(t.begin() - lastunary.begin())));
+ lastunary.data(),
+ static_cast<size_t>(t.data() - lastunary.data())));
return NULL;
}
}
@@ -2354,8 +2355,8 @@ Regexp* Regexp::Parse(const StringPiece& s, ParseFlags global_flags,
// Not allowed to stack repetition operators.
status->set_code(kRegexpRepeatOp);
status->set_error_arg(StringPiece(
- lastunary.begin(),
- static_cast<size_t>(t.begin() - lastunary.begin())));
+ lastunary.data(),
+ static_cast<size_t>(t.data() - lastunary.data())));
return NULL;
}
}
diff --git a/re2/prog.cc b/re2/prog.cc
index 5155943..cc35917 100644
--- a/re2/prog.cc
+++ b/re2/prog.cc
@@ -288,24 +288,24 @@ uint32_t Prog::EmptyFlags(const StringPiece& text, const char* p) {
int flags = 0;
// ^ and \A
- if (p == text.begin())
+ if (p == text.data())
flags |= kEmptyBeginText | kEmptyBeginLine;
else if (p[-1] == '\n')
flags |= kEmptyBeginLine;
// $ and \z
- if (p == text.end())
+ if (p == text.data() + text.size())
flags |= kEmptyEndText | kEmptyEndLine;
- else if (p < text.end() && p[0] == '\n')
+ else if (p < text.data() + text.size() && p[0] == '\n')
flags |= kEmptyEndLine;
// \b and \B
- if (p == text.begin() && p == text.end()) {
+ if (p == text.data() && p == text.data() + text.size()) {
// no word boundary here
- } else if (p == text.begin()) {
+ } else if (p == text.data()) {
if (IsWordChar(p[0]))
flags |= kEmptyWordBoundary;
- } else if (p == text.end()) {
+ } else if (p == text.data() + text.size()) {
if (IsWordChar(p[-1]))
flags |= kEmptyWordBoundary;
} else {
diff --git a/re2/re2.cc b/re2/re2.cc
index a4b4992..ef02d82 100644
--- a/re2/re2.cc
+++ b/re2/re2.cc
@@ -377,8 +377,8 @@ bool RE2::Replace(std::string* str,
if (!re.Rewrite(&s, rewrite, vec, nvec))
return false;
- assert(vec[0].begin() >= str->data());
- assert(vec[0].end() <= str->data()+str->size());
+ assert(vec[0].data() >= str->data());
+ assert(vec[0].data() + vec[0].size() <= str->data() + str->size());
str->replace(vec[0].data() - str->data(), vec[0].size(), s);
return true;
}
@@ -406,9 +406,9 @@ int RE2::GlobalReplace(std::string* str,
if (!re.Match(*str, static_cast<size_t>(p - str->data()),
str->size(), UNANCHORED, vec, nvec))
break;
- if (p < vec[0].begin())
- out.append(p, vec[0].begin() - p);
- if (vec[0].begin() == lastend && vec[0].size() == 0) {
+ if (p < vec[0].data())
+ out.append(p, vec[0].data() - p);
+ if (vec[0].data() == lastend && vec[0].size() == 0) {
// Disallow empty match at end of last match: skip ahead.
//
// fullrune() takes int, not ptrdiff_t. However, it just looks
@@ -439,7 +439,7 @@ int RE2::GlobalReplace(std::string* str,
continue;
}
re.Rewrite(&out, rewrite, vec, nvec);
- p = vec[0].end();
+ p = vec[0].data() + vec[0].size();
lastend = p;
count++;
}
diff --git a/re2/testing/backtrack.cc b/re2/testing/backtrack.cc
index ae9fd82..6cde42d 100644
--- a/re2/testing/backtrack.cc
+++ b/re2/testing/backtrack.cc
@@ -105,7 +105,7 @@ bool Backtracker::Search(const StringPiece& text, const StringPiece& context,
StringPiece* submatch, int nsubmatch) {
text_ = text;
context_ = context;
- if (context_.begin() == NULL)
+ if (context_.data() == NULL)
context_ = text;
if (prog_->anchor_start() && text.begin() > context_.begin())
return false;
@@ -137,14 +137,14 @@ bool Backtracker::Search(const StringPiece& text, const StringPiece& context,
// Anchored search must start at text.begin().
if (anchored_) {
- cap_[0] = text.begin();
- return Visit(prog_->start(), text.begin());
+ cap_[0] = text.data();
+ return Visit(prog_->start(), text.data());
}
// Unanchored search, starting from each possible text position.
// Notice that we have to try the empty string at the end of
// the text, so the loop condition is p <= text.end(), not p < text.end().
- for (const char* p = text.begin(); p <= text.end(); p++) {
+ for (const char* p = text.data(); p <= text.data() + text.size(); p++) {
cap_[0] = p;
if (Visit(prog_->start(), p)) // Match must be leftmost; done.
return true;
@@ -158,8 +158,8 @@ bool Backtracker::Visit(int id, const char* p) {
// Check bitmap. If we've already explored from here,
// either it didn't match or it did but we're hoping for a better match.
// Either way, don't go down that road again.
- CHECK(p <= text_.end());
- size_t n = id*(text_.size()+1) + (p - text_.begin());
+ CHECK(p <= text_.data() + text_.size());
+ size_t n = id*(text_.size()+1) + (p - text_.data());
CHECK_LT(n/32, nvisited_);
if (visited_[n/32] & (1 << (n&31)))
return false;
@@ -182,7 +182,7 @@ bool Backtracker::Try(int id, const char* p) {
// Pick out byte at current position. If at end of string,
// have to explore in hope of finishing a match. Use impossible byte -1.
int c = -1;
- if (p < text_.end())
+ if (p < text_.data() + text_.size())
c = *p & 0xFF;
Prog::Inst* ip = prog_->inst(id);
@@ -224,11 +224,12 @@ bool Backtracker::Try(int id, const char* p) {
case kInstMatch:
// We found a match. If it's the best so far, record the
// parameters in the caller's submatch_ array.
- if (endmatch_ && p != context_.end())
+ if (endmatch_ && p != context_.data() + context_.size())
return false;
cap_[1] = p;
- if (submatch_[0].data() == NULL || // First match so far ...
- (longest_ && p > submatch_[0].end())) { // ... or better match
+ if (submatch_[0].data() == NULL ||
+ (longest_ && p > submatch_[0].data() + submatch_[0].size())) {
+ // First match so far - or better match.
for (int i = 0; i < nsubmatch_; i++)
submatch_[i] = StringPiece(
cap_[2 * i], static_cast<size_t>(cap_[2 * i + 1] - cap_[2 * i]));
diff --git a/re2/testing/exhaustive_tester.cc b/re2/testing/exhaustive_tester.cc
index 47950ba..cadd2b4 100644
--- a/re2/testing/exhaustive_tester.cc
+++ b/re2/testing/exhaustive_tester.cc
@@ -62,7 +62,7 @@ static void PrintResult(const RE2& re, const StringPiece& input, RE2::Anchor anc
for (int i = 0; i < n; i++) {
if (i > 0)
printf(" ");
- if (m[i].begin() == NULL)
+ if (m[i].data() == NULL)
printf("-");
else
printf("%td-%td",
diff --git a/re2/testing/regexp_generator.cc b/re2/testing/regexp_generator.cc
index 1e4d3da..d156c88 100644
--- a/re2/testing/regexp_generator.cc
+++ b/re2/testing/regexp_generator.cc
@@ -241,7 +241,7 @@ void RegexpGenerator::RunPostfix(const std::vector<std::string>& post) {
std::vector<std::string> Explode(const StringPiece& s) {
std::vector<std::string> v;
- for (const char *q = s.begin(); q < s.end(); ) {
+ for (const char *q = s.data(); q < s.data() + s.size(); ) {
const char* p = q;
Rune r;
q += chartorune(&r, q);
@@ -259,8 +259,8 @@ std::vector<std::string> Split(const StringPiece& sep, const StringPiece& s) {
if (sep.size() == 0)
return Explode(s);
- const char *p = s.begin();
- for (const char *q = s.begin(); q + sep.size() <= s.end(); q++) {
+ const char *p = s.data();
+ for (const char *q = s.data(); q + sep.size() <= s.data() + s.size(); q++) {
if (StringPiece(q, sep.size()) == sep) {
v.push_back(std::string(p, q - p));
p = q + sep.size();
@@ -268,8 +268,8 @@ std::vector<std::string> Split(const StringPiece& sep, const StringPiece& s) {
continue;
}
}
- if (p < s.end())
- v.push_back(std::string(p, s.end() - p));
+ if (p < s.data() + s.size())
+ v.push_back(std::string(p, s.data() + s.size() - p));
return v;
}
diff --git a/re2/testing/tester.cc b/re2/testing/tester.cc
index d676d9a..f08d717 100644
--- a/re2/testing/tester.cc
+++ b/re2/testing/tester.cc
@@ -99,7 +99,7 @@ typedef TestInstance::Result Result;
// where a and b are the starting and ending offsets of s in text.
static std::string FormatCapture(const StringPiece& text,
const StringPiece& s) {
- if (s.begin() == NULL)
+ if (s.data() == NULL)
return "(?,?)";
return StringPrintf("(%td,%td)",
s.begin() - text.begin(), s.end() - text.begin());
@@ -489,7 +489,7 @@ static bool ResultOkay(const Result& r, const Result& correct) {
return false;
if (r.have_submatch || r.have_submatch0) {
for (int i = 0; i < kMaxSubmatch; i++) {
- if (correct.submatch[i].begin() != r.submatch[i].begin() ||
+ if (correct.submatch[i].data() != r.submatch[i].data() ||
correct.submatch[i].size() != r.submatch[i].size())
return false;
if (!r.have_submatch)
@@ -555,8 +555,8 @@ bool TestInstance::RunCase(const StringPiece& text, const StringPiece& context,
}
}
for (int i = 0; i < 1+num_captures_; i++) {
- if (r.submatch[i].begin() != correct.submatch[i].begin() ||
- r.submatch[i].end() != correct.submatch[i].end()) {
+ if (r.submatch[i].data() != correct.submatch[i].data() ||
+ r.submatch[i].size() != correct.submatch[i].size()) {
LOG(INFO) <<
StringPrintf(" $%d: should be %s is %s",
i,
diff --git a/re2_test.bzl b/re2_test.bzl
deleted file mode 100644
index c0eb654..0000000
--- a/re2_test.bzl
+++ /dev/null
@@ -1,12 +0,0 @@
-# Copyright 2009 The RE2 Authors. All Rights Reserved.
-# Use of this source code is governed by a BSD-style
-# license that can be found in the LICENSE file.
-
-# Defines a Bazel macro that instantiates a native cc_test rule for an RE2 test.
-def re2_test(name, deps=[], size="medium"):
- native.cc_test(
- name=name,
- srcs=["re2/testing/%s.cc" % (name)],
- deps=[":test"] + deps,
- size=size,
- )
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-22 15:11:12 +0000