mirror of
https://github.com/red0124/ssp.git
synced 2025-01-23 13:05:20 +01:00
WIP, added multiline restriction, fixed a few bugs for multiline, updated unit tests
This commit is contained in:
parent
2985027505
commit
2dbc21780f
@ -230,6 +230,15 @@ private:
|
||||
}
|
||||
}
|
||||
|
||||
void set_error_multiline_limit_reached() {
|
||||
if constexpr (string_error) {
|
||||
error_.clear();
|
||||
error_.append("multiline limit reached.");
|
||||
} else {
|
||||
error_ = true;
|
||||
}
|
||||
}
|
||||
|
||||
void set_error_invalid_conversion(const string_range msg, size_t pos) {
|
||||
if constexpr (string_error) {
|
||||
error_.clear();
|
||||
|
||||
@ -9,13 +9,16 @@
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
// TODO remove
|
||||
#include <iostream>
|
||||
|
||||
namespace ss {
|
||||
|
||||
template <typename... Matchers>
|
||||
class parser {
|
||||
constexpr static auto string_error = setup<Matchers...>::string_error;
|
||||
constexpr static auto multiline = setup<Matchers...>::multiline;
|
||||
|
||||
using multiline = typename setup<Matchers...>::multiline;
|
||||
using error_type = ss::ternary_t<string_error, std::string, bool>;
|
||||
|
||||
public:
|
||||
@ -324,7 +327,7 @@ private:
|
||||
helper_buffer_{other.helper_buffer_}, converter_{std::move(
|
||||
other.converter_)},
|
||||
next_line_converter_{std::move(other.next_line_converter_)},
|
||||
size_{other.size_},
|
||||
size_{other.size_}, next_line_size_{other.size_},
|
||||
helper_size_{other.helper_size_}, delim_{std::move(other.delim_)},
|
||||
file_{other.file_}, crlf_{other.crlf_} {
|
||||
other.buffer_ = nullptr;
|
||||
@ -341,6 +344,7 @@ private:
|
||||
converter_ = std::move(other.converter_);
|
||||
next_line_converter_ = std::move(other.next_line_converter_);
|
||||
size_ = other.size_;
|
||||
next_line_size_ = other.next_line_size_;
|
||||
helper_size_ = other.helper_size_;
|
||||
delim_ = std::move(other.delim_);
|
||||
file_ = other.file_;
|
||||
@ -370,16 +374,23 @@ private:
|
||||
reader& operator=(const reader& other) = delete;
|
||||
|
||||
bool read_next() {
|
||||
ssize_t ssize = getline(&next_line_buffer_, &size_, file_);
|
||||
memset(next_line_buffer_, '\0', next_line_size_);
|
||||
ssize_t ssize =
|
||||
getline(&next_line_buffer_, &next_line_size_, file_);
|
||||
|
||||
if (ssize == -1) {
|
||||
return false;
|
||||
}
|
||||
|
||||
size_t size = remove_eol(next_line_buffer_, ssize);
|
||||
size_t limit = 0;
|
||||
|
||||
if constexpr (multiline && setup<Matchers...>::escape::enabled) {
|
||||
if constexpr (multiline::enabled &&
|
||||
setup<Matchers...>::escape::enabled) {
|
||||
while (escaped_eol(size)) {
|
||||
if (multiline_limit_reached(limit)) {
|
||||
return true;
|
||||
}
|
||||
if (!append_line(next_line_buffer_, size)) {
|
||||
return false;
|
||||
}
|
||||
@ -388,8 +399,12 @@ private:
|
||||
|
||||
next_line_converter_.split(next_line_buffer_, delim_);
|
||||
|
||||
if constexpr (multiline && setup<Matchers...>::quote::enabled) {
|
||||
if constexpr (multiline::enabled &&
|
||||
setup<Matchers...>::quote::enabled) {
|
||||
while (unterminated_quote()) {
|
||||
if (multiline_limit_reached(limit)) {
|
||||
return true;
|
||||
}
|
||||
if (!append_line(next_line_buffer_, size)) {
|
||||
return false;
|
||||
}
|
||||
@ -402,9 +417,20 @@ private:
|
||||
|
||||
void update() {
|
||||
std::swap(buffer_, next_line_buffer_);
|
||||
std::swap(size_, next_line_size_);
|
||||
std::swap(converter_, next_line_converter_);
|
||||
}
|
||||
|
||||
bool multiline_limit_reached(size_t& limit) {
|
||||
if constexpr (multiline::size > 0) {
|
||||
if (limit++ >= multiline::size) {
|
||||
next_line_converter_.set_error_multiline_limit_reached();
|
||||
return true;
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
bool escaped_eol(size_t size) {
|
||||
const char* curr;
|
||||
for (curr = next_line_buffer_ + size - 1;
|
||||
@ -422,12 +448,15 @@ private:
|
||||
return false;
|
||||
}
|
||||
|
||||
void undo_remove_eol(size_t& string_end) {
|
||||
void undo_remove_eol(char* buffer, size_t& string_end) {
|
||||
if (next_line_converter_.unterminated_quote()) {
|
||||
string_end -= next_line_converter_.splitter_.escaped_;
|
||||
}
|
||||
if (crlf_) {
|
||||
std::copy_n("\r\n\0", 3, next_line_buffer_ + string_end);
|
||||
std::copy_n("\r\n\0", 3, buffer + string_end);
|
||||
string_end += 2;
|
||||
} else {
|
||||
std::copy_n("\n\0", 2, next_line_buffer_ + string_end);
|
||||
std::copy_n("\n\0", 2, buffer + string_end);
|
||||
string_end += 1;
|
||||
}
|
||||
}
|
||||
@ -447,15 +476,15 @@ private:
|
||||
|
||||
void realloc_concat(char*& first, size_t& first_size,
|
||||
const char* const second, size_t second_size) {
|
||||
first = static_cast<char*>(realloc(static_cast<void*>(first),
|
||||
first_size + second_size + 2));
|
||||
|
||||
next_line_size_ = first_size + second_size + 2;
|
||||
first = static_cast<char*>(
|
||||
realloc(static_cast<void*>(first), next_line_size_));
|
||||
std::copy_n(second, second_size + 1, first + first_size);
|
||||
first_size += second_size;
|
||||
}
|
||||
|
||||
bool append_line(char*& dst_buffer, size_t& dst_size) {
|
||||
undo_remove_eol(dst_size);
|
||||
undo_remove_eol(dst_buffer, dst_size);
|
||||
|
||||
ssize_t ssize = getline(&helper_buffer_, &helper_size_, file_);
|
||||
if (ssize == -1) {
|
||||
@ -478,6 +507,7 @@ private:
|
||||
converter<Matchers...> next_line_converter_;
|
||||
|
||||
size_t size_{0};
|
||||
size_t next_line_size_{0};
|
||||
size_t helper_size_{0};
|
||||
|
||||
std::string delim_;
|
||||
|
||||
@ -67,7 +67,11 @@ public:
|
||||
};
|
||||
|
||||
////////////////
|
||||
// setup parameters
|
||||
// setup
|
||||
////////////////
|
||||
|
||||
////////////////
|
||||
// matcher
|
||||
////////////////
|
||||
|
||||
template <char C>
|
||||
@ -85,15 +89,6 @@ struct trim_right : matcher<Cs...> {};
|
||||
template <char... Cs>
|
||||
struct escape : matcher<Cs...> {};
|
||||
|
||||
// TODO add limit
|
||||
class multiline;
|
||||
|
||||
class string_error;
|
||||
|
||||
////////////////
|
||||
// setup implementation
|
||||
////////////////
|
||||
|
||||
template <typename T, template <char...> class Template>
|
||||
struct is_instance_of_matcher : std::false_type {};
|
||||
|
||||
@ -128,6 +123,54 @@ struct get_matcher<Matcher> {
|
||||
template <template <char...> class Matcher, typename... Ts>
|
||||
using get_matcher_t = typename get_matcher<Matcher, Ts...>::type;
|
||||
|
||||
////////////////
|
||||
// multiline
|
||||
////////////////
|
||||
|
||||
template <size_t S, bool B = true>
|
||||
struct multiline_restricted {
|
||||
constexpr static auto size = S;
|
||||
constexpr static auto enabled = B;
|
||||
};
|
||||
|
||||
using multiline = multiline_restricted<0>;
|
||||
|
||||
template <typename T>
|
||||
struct is_instance_of_multiline : std::false_type {};
|
||||
|
||||
template <size_t S, bool B>
|
||||
struct is_instance_of_multiline<multiline_restricted<S, B>> : std::true_type {};
|
||||
|
||||
template <typename T>
|
||||
using is_instance_of_multiline_t = typename is_instance_of_multiline<T>::type;
|
||||
|
||||
template <typename... Ts>
|
||||
struct get_multiline;
|
||||
|
||||
template <typename T, typename... Ts>
|
||||
struct get_multiline<T, Ts...> {
|
||||
using type = ternary_t<is_instance_of_multiline<T>::value, T,
|
||||
typename get_multiline<Ts...>::type>;
|
||||
};
|
||||
|
||||
template <>
|
||||
struct get_multiline<> {
|
||||
using type = multiline_restricted<0, false>;
|
||||
};
|
||||
|
||||
template <typename... Ts>
|
||||
using get_multiline_t = typename get_multiline<Ts...>::type;
|
||||
|
||||
////////////////
|
||||
// string_error
|
||||
////////////////
|
||||
|
||||
class string_error;
|
||||
|
||||
////////////////
|
||||
// setup implementation
|
||||
////////////////
|
||||
|
||||
template <typename... Ts>
|
||||
struct setup {
|
||||
private:
|
||||
@ -139,14 +182,12 @@ private:
|
||||
is_instance_of_matcher_t<T, trim_left>,
|
||||
is_instance_of_matcher_t<T, trim_right>> {};
|
||||
|
||||
template <typename T>
|
||||
struct is_multiline : std::is_same<T, multiline> {};
|
||||
|
||||
template <typename T>
|
||||
struct is_string_error : std::is_same<T, string_error> {};
|
||||
|
||||
constexpr static auto count_matcher = count_v<is_matcher, Ts...>;
|
||||
constexpr static auto count_multiline = count_v<is_multiline, Ts...>;
|
||||
constexpr static auto count_multiline =
|
||||
count_v<is_instance_of_multiline, Ts...>;
|
||||
constexpr static auto count_string_error = count_v<is_string_error, Ts...>;
|
||||
|
||||
constexpr static auto number_of_valid_setup_types =
|
||||
@ -163,7 +204,7 @@ public:
|
||||
using trim_left = ternary_t<trim_all::enabled, trim_all, trim_left_only>;
|
||||
using trim_right = ternary_t<trim_all::enabled, trim_all, trim_right_only>;
|
||||
|
||||
constexpr static bool multiline = (count_multiline == 1);
|
||||
using multiline = get_multiline_t<Ts...>;
|
||||
constexpr static bool string_error = (count_string_error == 1);
|
||||
|
||||
private:
|
||||
@ -181,7 +222,8 @@ private:
|
||||
#undef ASSERT_MSG
|
||||
|
||||
static_assert(
|
||||
!multiline || (multiline && (quote::enabled || escape::enabled)),
|
||||
!multiline::enabled ||
|
||||
(multiline::enabled && (quote::enabled || escape::enabled)),
|
||||
"to enable multiline either quote or escape need to be enabled");
|
||||
|
||||
static_assert(!(trim_all::enabled && trim_left_only::enabled) &&
|
||||
|
||||
@ -9,6 +9,9 @@
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
// TODO remove
|
||||
#include <iostream>
|
||||
|
||||
namespace ss {
|
||||
|
||||
template <typename... Ts>
|
||||
@ -82,7 +85,13 @@ private:
|
||||
return split_data_;
|
||||
}
|
||||
|
||||
std::cout << "======================" << std::endl;
|
||||
std::cout << "resplitting" << std::endl;
|
||||
resplitting_ = true;
|
||||
begin_ = line_ + begin;
|
||||
size_t end = end_ - old_line - escaped_;
|
||||
end_ = line_ + end;
|
||||
curr_ = end_;
|
||||
}
|
||||
}
|
||||
|
||||
@ -284,6 +293,12 @@ private:
|
||||
void read(const Delim& delim) {
|
||||
escaped_ = 0;
|
||||
if constexpr (quote::enabled) {
|
||||
if (resplitting_) {
|
||||
resplitting_ = false;
|
||||
++begin_;
|
||||
read_quoted(delim);
|
||||
return;
|
||||
}
|
||||
if (quote::match(*begin_)) {
|
||||
curr_ = end_ = ++begin_;
|
||||
read_quoted(delim);
|
||||
@ -321,7 +336,9 @@ private:
|
||||
template <typename Delim>
|
||||
void read_quoted(const Delim& delim) {
|
||||
if constexpr (quote::enabled) {
|
||||
std::cout << "start loop: " << std::endl;
|
||||
while (true) {
|
||||
std::cout << "- " << *end_ << std::endl;
|
||||
if (!quote::match(*end_)) {
|
||||
if constexpr (escape::enabled) {
|
||||
if (escape::match(*end_)) {
|
||||
@ -334,6 +351,7 @@ private:
|
||||
// unterminated quote error
|
||||
// eg: ..."hell\0 -> quote not terminated
|
||||
if (*end_ == '\0') {
|
||||
shift_and_set_current();
|
||||
set_error_unterminated_quote();
|
||||
split_data_.emplace_back(line_, begin_);
|
||||
done_ = true;
|
||||
@ -381,9 +399,11 @@ private:
|
||||
// members
|
||||
////////////////
|
||||
|
||||
public:
|
||||
error_type error_{};
|
||||
bool unterminated_quote_{false};
|
||||
bool done_;
|
||||
bool done_{true};
|
||||
bool resplitting_{false};
|
||||
size_t escaped_{0};
|
||||
split_data split_data_;
|
||||
|
||||
|
||||
@ -1,9 +1,9 @@
|
||||
test_sources = files([
|
||||
'test_main.cpp',
|
||||
'test_splitter.cpp',
|
||||
'test_converter.cpp',
|
||||
#'test_splitter.cpp',
|
||||
#'test_converter.cpp',
|
||||
'test_parser.cpp',
|
||||
'test_extractions.cpp',
|
||||
#'test_extractions.cpp',
|
||||
])
|
||||
|
||||
doctest_proj = subproject('doctest')
|
||||
|
||||
@ -8,10 +8,9 @@
|
||||
#include <doctest.h>
|
||||
#endif
|
||||
|
||||
class buffer {
|
||||
struct buffer {
|
||||
char* data_{nullptr};
|
||||
|
||||
public:
|
||||
char* operator()(const char* data) {
|
||||
if (data_) {
|
||||
delete[] data_;
|
||||
|
||||
@ -66,7 +66,7 @@ TEST_CASE("parser test various cases") {
|
||||
i.emplace_back(ss::to_object<X>(a));
|
||||
}
|
||||
|
||||
CHECK(std::equal(i.begin(), i.end(), data.begin()));
|
||||
CHECK_EQ(i, data);
|
||||
}
|
||||
|
||||
{
|
||||
@ -80,7 +80,7 @@ TEST_CASE("parser test various cases") {
|
||||
i.emplace_back(ss::to_object<X>(a));
|
||||
}
|
||||
|
||||
CHECK(std::equal(i.begin(), i.end(), data.begin() + 1));
|
||||
CHECK_EQ(i, data);
|
||||
}
|
||||
|
||||
{
|
||||
@ -91,7 +91,7 @@ TEST_CASE("parser test various cases") {
|
||||
i.push_back(p.get_object<X, int, double, std::string>());
|
||||
}
|
||||
|
||||
CHECK(std::equal(i.begin(), i.end(), data.begin()));
|
||||
CHECK_EQ(i, data);
|
||||
}
|
||||
|
||||
{
|
||||
@ -103,7 +103,7 @@ TEST_CASE("parser test various cases") {
|
||||
i.push_back(p.get_object<X, tup>());
|
||||
}
|
||||
|
||||
CHECK(std::equal(i.begin(), i.end(), data.begin()));
|
||||
CHECK_EQ(i, data);
|
||||
}
|
||||
|
||||
{
|
||||
@ -114,7 +114,7 @@ TEST_CASE("parser test various cases") {
|
||||
i.push_back(p.get_next<X>());
|
||||
}
|
||||
|
||||
CHECK(std::equal(i.begin(), i.end(), data.begin()));
|
||||
CHECK_EQ(i, data);
|
||||
}
|
||||
|
||||
{
|
||||
@ -132,7 +132,7 @@ TEST_CASE("parser test various cases") {
|
||||
std::vector<X> expected = data;
|
||||
std::remove_if(expected.begin(), expected.end(),
|
||||
[](const X& x) { return x.i == excluded; });
|
||||
CHECK(std::equal(i.begin(), i.end(), expected.begin()));
|
||||
CHECK_EQ(i, data);
|
||||
}
|
||||
|
||||
{
|
||||
@ -146,7 +146,7 @@ TEST_CASE("parser test various cases") {
|
||||
}
|
||||
}
|
||||
std::vector<X> expected = {{3, 4, "y"}};
|
||||
CHECK(std::equal(i.begin(), i.end(), expected.begin()));
|
||||
CHECK_EQ(i, data);
|
||||
}
|
||||
|
||||
{
|
||||
@ -194,7 +194,7 @@ TEST_CASE("parser test composite conversion") {
|
||||
auto expect_error = [](auto error) { CHECK(!error.empty()); };
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(!p.eof());
|
||||
REQUIRE_FALSE(p.eof());
|
||||
|
||||
{
|
||||
constexpr static auto expectedData = std::tuple{10, 'a', 11.1};
|
||||
@ -209,11 +209,11 @@ TEST_CASE("parser test composite conversion") {
|
||||
.values();
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(!d1);
|
||||
REQUIRE(!d2);
|
||||
REQUIRE_FALSE(d1);
|
||||
REQUIRE_FALSE(d2);
|
||||
REQUIRE(d3);
|
||||
REQUIRE(!d4);
|
||||
CHECK(*d3 == expectedData);
|
||||
REQUIRE_FALSE(d4);
|
||||
CHECK_EQ(*d3, expectedData);
|
||||
}
|
||||
|
||||
{
|
||||
@ -234,10 +234,10 @@ TEST_CASE("parser test composite conversion") {
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(d1);
|
||||
REQUIRE(!d2);
|
||||
REQUIRE(!d3);
|
||||
REQUIRE(!d4);
|
||||
CHECK(*d1 == expectedData);
|
||||
REQUIRE_FALSE(d2);
|
||||
REQUIRE_FALSE(d3);
|
||||
REQUIRE_FALSE(d4);
|
||||
CHECK_EQ(*d1 ,expectedData);
|
||||
}
|
||||
|
||||
{
|
||||
@ -252,12 +252,12 @@ TEST_CASE("parser test composite conversion") {
|
||||
.or_else<int, char, double>(fail)
|
||||
.values();
|
||||
|
||||
REQUIRE(!p.valid());
|
||||
REQUIRE(!d1);
|
||||
REQUIRE(!d2);
|
||||
REQUIRE(!d3);
|
||||
REQUIRE(!d4);
|
||||
REQUIRE(!d5);
|
||||
REQUIRE_FALSE(p.valid());
|
||||
REQUIRE_FALSE(d1);
|
||||
REQUIRE_FALSE(d2);
|
||||
REQUIRE_FALSE(d3);
|
||||
REQUIRE_FALSE(d4);
|
||||
REQUIRE_FALSE(d5);
|
||||
}
|
||||
|
||||
{
|
||||
@ -272,7 +272,7 @@ TEST_CASE("parser test composite conversion") {
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(d1);
|
||||
REQUIRE(!d2);
|
||||
REQUIRE_FALSE(d2);
|
||||
}
|
||||
|
||||
{
|
||||
@ -283,9 +283,9 @@ TEST_CASE("parser test composite conversion") {
|
||||
.values();
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(!d1);
|
||||
REQUIRE_FALSE(d1);
|
||||
REQUIRE(d2);
|
||||
CHECK(d2->tied() == std::tuple{1, 11.1, 'a'});
|
||||
CHECK_EQ(d2->tied(), std::tuple{1, 11.1, 'a'});
|
||||
}
|
||||
|
||||
{
|
||||
@ -300,12 +300,12 @@ TEST_CASE("parser test composite conversion") {
|
||||
.on_error(expect_error)
|
||||
.values();
|
||||
|
||||
REQUIRE(!p.valid());
|
||||
REQUIRE(!d1);
|
||||
REQUIRE(!d2);
|
||||
REQUIRE(!d3);
|
||||
REQUIRE(!d4);
|
||||
REQUIRE(!d5);
|
||||
REQUIRE_FALSE(p.valid());
|
||||
REQUIRE_FALSE(d1);
|
||||
REQUIRE_FALSE(d2);
|
||||
REQUIRE_FALSE(d3);
|
||||
REQUIRE_FALSE(d4);
|
||||
REQUIRE_FALSE(d5);
|
||||
}
|
||||
|
||||
{
|
||||
@ -319,12 +319,12 @@ TEST_CASE("parser test composite conversion") {
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(d1);
|
||||
REQUIRE(!d2);
|
||||
CHECK(*d1 == std::tuple{10, std::nullopt});
|
||||
REQUIRE_FALSE(d2);
|
||||
CHECK_EQ(*d1, std::tuple{10, std::nullopt});
|
||||
}
|
||||
|
||||
{
|
||||
REQUIRE(!p.eof());
|
||||
REQUIRE_FALSE(p.eof());
|
||||
|
||||
auto [d1, d2] = p.try_next<int, std::variant<int, std::string>>()
|
||||
.on_error(fail)
|
||||
@ -334,8 +334,8 @@ TEST_CASE("parser test composite conversion") {
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(d1);
|
||||
REQUIRE(!d2);
|
||||
CHECK(*d1 == std::tuple{11, std::variant<int, std::string>{"junk"}});
|
||||
REQUIRE_FALSE(d2);
|
||||
CHECK_EQ(*d1, std::tuple{11, std::variant<int, std::string>{"junk"}});
|
||||
}
|
||||
|
||||
{
|
||||
@ -346,12 +346,12 @@ TEST_CASE("parser test composite conversion") {
|
||||
.values();
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(d1);
|
||||
REQUIRE(!d2);
|
||||
CHECK(d1->tied() == std::tuple{10, 11.1, 'c'});
|
||||
REQUIRE_FALSE(d2);
|
||||
CHECK_EQ(d1->tied(), std::tuple{10, 11.1, 'c'});
|
||||
}
|
||||
|
||||
{
|
||||
REQUIRE(!p.eof());
|
||||
REQUIRE_FALSE(p.eof());
|
||||
|
||||
auto [d1, d2, d3, d4] =
|
||||
p.try_next<int, int>([] { return false; })
|
||||
@ -361,11 +361,11 @@ TEST_CASE("parser test composite conversion") {
|
||||
.values();
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(!d1);
|
||||
REQUIRE(!d2);
|
||||
REQUIRE_FALSE(d1);
|
||||
REQUIRE_FALSE(d2);
|
||||
REQUIRE(d3);
|
||||
REQUIRE(!d4);
|
||||
CHECK(d3.value() == std::tuple{10, 20});
|
||||
REQUIRE_FALSE(d4);
|
||||
CHECK_EQ(d3.value(), std::tuple{10, 20});
|
||||
}
|
||||
|
||||
{
|
||||
@ -379,11 +379,11 @@ TEST_CASE("parser test composite conversion") {
|
||||
.values();
|
||||
|
||||
REQUIRE(p.valid());
|
||||
REQUIRE(!d1);
|
||||
REQUIRE(!d2);
|
||||
REQUIRE_FALSE(d1);
|
||||
REQUIRE_FALSE(d2);
|
||||
REQUIRE(d3);
|
||||
REQUIRE(!d4);
|
||||
CHECK(d3->tied() == std::tuple{10, 22.2, 'f'});
|
||||
REQUIRE_FALSE(d4);
|
||||
CHECK_EQ(d3->tied(), std::tuple{10, 22.2, 'f'});
|
||||
}
|
||||
|
||||
CHECK(p.eof());
|
||||
@ -446,7 +446,7 @@ TEST_CASE("parser test the moving of parsed values") {
|
||||
|
||||
ss::parser p{f.name, ","};
|
||||
auto x = p.get_next<my_string>();
|
||||
CHECK(move_called < 3);
|
||||
CHECK_LT(move_called, 3);
|
||||
move_called_one_col = move_called;
|
||||
move_called = 0;
|
||||
}
|
||||
@ -461,21 +461,21 @@ TEST_CASE("parser test the moving of parsed values") {
|
||||
|
||||
ss::parser p{f.name, ","};
|
||||
auto x = p.get_next<my_string, my_string, my_string>();
|
||||
CHECK(move_called <= 3 * move_called_one_col);
|
||||
CHECK_LE(move_called, 3 * move_called_one_col);
|
||||
move_called = 0;
|
||||
}
|
||||
|
||||
{
|
||||
ss::parser p{f.name, ","};
|
||||
auto x = p.get_object<xyz, my_string, my_string, my_string>();
|
||||
CHECK(move_called <= 6 * move_called_one_col);
|
||||
CHECK_LE(move_called, 6 * move_called_one_col);
|
||||
move_called = 0;
|
||||
}
|
||||
|
||||
{
|
||||
ss::parser p{f.name, ","};
|
||||
auto x = p.get_next<xyz>();
|
||||
CHECK(move_called <= 6 * move_called_one_col);
|
||||
CHECK_LE(move_called, 6 * move_called_one_col);
|
||||
move_called = 0;
|
||||
}
|
||||
}
|
||||
@ -503,10 +503,10 @@ TEST_CASE("parser test error mode") {
|
||||
|
||||
ss::parser<ss::string_error> p(f.name, ",");
|
||||
|
||||
REQUIRE(!p.eof());
|
||||
REQUIRE_FALSE(p.eof());
|
||||
p.get_next<int>();
|
||||
CHECK(!p.valid());
|
||||
CHECK(!p.error_msg().empty());
|
||||
CHECK_FALSE(p.valid());
|
||||
CHECK_FALSE(p.error_msg().empty());
|
||||
}
|
||||
|
||||
std::string no_quote(const std::string& s) {
|
||||
@ -516,7 +516,7 @@ std::string no_quote(const std::string& s) {
|
||||
return s;
|
||||
}
|
||||
|
||||
TEST_CASE("parser test csv on multiple lines with quotes") {
|
||||
TEST_CASE("parser test csv on multiple lines with quotes zzz") {
|
||||
unique_file_name f;
|
||||
std::vector<X> data = {{1, 2, "\"x\nx\nx\""}, {3, 4, "\"y\ny\ny\""},
|
||||
{5, 6, "\"z\nz\""}, {7, 8, "\"u\"\"\""},
|
||||
@ -537,7 +537,7 @@ TEST_CASE("parser test csv on multiple lines with quotes") {
|
||||
i.emplace_back(ss::to_object<X>(a));
|
||||
}
|
||||
|
||||
CHECK(std::equal(i.begin(), i.end(), data.begin()));
|
||||
CHECK_EQ(i, data);
|
||||
|
||||
ss::parser<ss::quote<'"'>> p_no_multiline{f.name, ","};
|
||||
while (!p.eof()) {
|
||||
@ -551,10 +551,10 @@ std::string no_escape(std::string& s) {
|
||||
return s;
|
||||
}
|
||||
|
||||
TEST_CASE("parser test csv on multiple lines with escapes") {
|
||||
TEST_CASE("parser test csv on multiple lines with escapes xxx") {
|
||||
unique_file_name f;
|
||||
std::vector<X> data = {{1, 2, "x\\\nx\\\nx"}, {3, 4, "y\\\ny\\\ny"},
|
||||
{5, 6, "z\\\nz"}, {7, 8, "u"},
|
||||
std::vector<X> data = {{1, 2, "x\\\nx\\\nx"}, {5, 6, "z\\\nz\\\nz"},
|
||||
{7, 8, "u"}, {3, 4, "y\\\ny\\\ny"},
|
||||
{9, 10, "v\\\\"}, {11, 12, "w\\\n"}};
|
||||
|
||||
make_and_write(f.name, data);
|
||||
@ -571,13 +571,78 @@ TEST_CASE("parser test csv on multiple lines with escapes") {
|
||||
while (!p.eof()) {
|
||||
auto a = p.get_next<int, double, std::string>();
|
||||
i.emplace_back(ss::to_object<X>(a));
|
||||
// std::cout << i.back().s << std::endl;
|
||||
}
|
||||
|
||||
CHECK(std::equal(i.begin(), i.end(), data.begin()));
|
||||
CHECK_EQ(i, data);
|
||||
|
||||
ss::parser<ss::escape<'\\'>> p_no_multiline{f.name, ","};
|
||||
while (!p.eof()) {
|
||||
auto a = p_no_multiline.get_next<int, double, std::string>();
|
||||
CHECK(!p.valid());
|
||||
CHECK_FALSE(p.valid());
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("parser test csv on multiple lines with quotes and escapes yyy") {
|
||||
unique_file_name f;
|
||||
{
|
||||
std::ofstream out{f.name};
|
||||
// out << "1,2,\"just\\\n\nstrings\"" << std::endl;
|
||||
out << "3,4,\"j\\\ns\n\\\nx\\\ny\ng\"" << std::endl;
|
||||
// out << "5,6,\"just\\\n\\\n\n\nstrings" << std::endl;
|
||||
// out << "7,8,\"just strings\"" << std::endl;
|
||||
// out << "9,10,just strings" << std::endl;
|
||||
}
|
||||
|
||||
ss::parser<ss::multiline, ss::escape<'\\'>, ss::quote<'"'>> p{f.name};
|
||||
std::vector<X> i;
|
||||
|
||||
while (!p.eof()) {
|
||||
auto a = p.get_next<int, double, std::string>();
|
||||
if (p.valid()) {
|
||||
i.emplace_back(ss::to_object<X>(a));
|
||||
}
|
||||
}
|
||||
|
||||
std::vector<X> data = {{1, 2, "just\n\nstrings"},
|
||||
{3, 4, "just\nsome\n\n\nstrings"},
|
||||
{9, 10, "just strings"}};
|
||||
|
||||
CHECK_EQ(i, data);
|
||||
}
|
||||
|
||||
/*
|
||||
TEST_CASE("parser test multiline restricted") {
|
||||
unique_file_name f;
|
||||
{
|
||||
std::ofstream out{f.name};
|
||||
//out << "1,2,\"just\n\nstrings\"" << std::endl;
|
||||
//out << "3,4,\"ju\n\n\nnk\"" << std::endl;
|
||||
//out << "5,6,just\\\n\\\nstrings" << std::endl;
|
||||
//out << "7,8,ju\\\n\\\n\\\nnk" << std::endl;
|
||||
//out << "9,10,\"just\\\n\nstrings\"" << std::endl;
|
||||
out << "11,12,\"ju\\\n|\n\n\n\n\nk\"" << std::endl;
|
||||
// out << "13,14,\"ju\\\n\\\n15,16\"\\\n\\\\\n\nnk\"" << std::endl;
|
||||
// out << "17,18,\"ju\\\n\\\n\\\n\\\\\n\nnk\"" << std::endl;
|
||||
out << "19,20,just strings" << std::endl;
|
||||
}
|
||||
|
||||
ss::parser<ss::multiline_restricted<120>, ss::quote<'"'>, ss::escape<'\\'>>
|
||||
p{f.name, ","};
|
||||
std::vector<X> i;
|
||||
|
||||
while (!p.eof()) {
|
||||
std::cout << "==========================" << std::endl;
|
||||
auto a = p.get_next<int, double, std::string>();
|
||||
if (p.valid()) {
|
||||
i.emplace_back(ss::to_object<X>(a));
|
||||
}
|
||||
}
|
||||
|
||||
std::vector<X> data = {{1, 2, "just\n\nstrings"},
|
||||
{5, 6, "just\n\nstrings"},
|
||||
{9, 10, "just\n\nstrings"},
|
||||
{19, 20, "just strings"}};
|
||||
CHECK(std::equal(i.begin(), i.end(), data.begin()));
|
||||
}
|
||||
*/
|
||||
|
||||
@ -541,7 +541,7 @@ public:
|
||||
};
|
||||
} /* ss */
|
||||
|
||||
TEST_CASE("splitter test unterminated quote") {
|
||||
TEST_CASE("splitter test resplit unterminated quote") {
|
||||
{
|
||||
ss::converter<ss::quote<'"'>> c;
|
||||
auto& s = c.splitter;
|
||||
@ -578,6 +578,7 @@ TEST_CASE("splitter test unterminated quote") {
|
||||
std::vector<std::string> expected{"just", "some", R"("just","some",")"};
|
||||
CHECK(words(vec) == expected);
|
||||
|
||||
buff.data_[strlen(buff.data_) - c.splitter.escaped_] = '\0';
|
||||
auto new_line = buff.append(R"(,dom","strings")");
|
||||
vec = c.resplit(new_line, strlen(new_line));
|
||||
CHECK(s.valid());
|
||||
@ -629,6 +630,27 @@ TEST_CASE("splitter test unterminated quote") {
|
||||
}
|
||||
}
|
||||
|
||||
{
|
||||
ss::converter<ss::quote<'"'>, ss::escape<'\\'>> c;
|
||||
auto& s = c.splitter;
|
||||
auto vec =
|
||||
expect_unterminated_quote(s, "3,4,"
|
||||
"\"just0\\\n1\\\n22\\\n33333x\\\n4");
|
||||
|
||||
std::vector<std::string> expected{"3", "4"};
|
||||
auto w = words(vec);
|
||||
w.pop_back();
|
||||
CHECK(w == expected);
|
||||
{
|
||||
buff.data_[strlen(buff.data_) - c.splitter.escaped_] = '\0';
|
||||
auto new_line = buff.append("\nx5strings\"");
|
||||
vec = c.resplit(new_line, strlen(new_line));
|
||||
CHECK(s.valid());
|
||||
CHECK(!s.unterminated_quote());
|
||||
expected = {"3", "4", "just0\n1\n22\n33333x\n4\nx5strings"};
|
||||
CHECK(words(vec) == expected);
|
||||
}
|
||||
}
|
||||
{
|
||||
ss::converter<ss::quote<'"'>, ss::escape<'\\'>> c;
|
||||
auto& s = c.splitter;
|
||||
@ -638,6 +660,7 @@ TEST_CASE("splitter test unterminated quote") {
|
||||
w.pop_back();
|
||||
CHECK(w == expected);
|
||||
{
|
||||
buff.data_[strlen(buff.data_) - c.splitter.escaped_] = '\0';
|
||||
auto new_line = buff.append(R"(n,dom",str\"ings)");
|
||||
vec = c.resplit(new_line, strlen(new_line));
|
||||
CHECK(s.valid());
|
||||
@ -650,17 +673,18 @@ TEST_CASE("splitter test unterminated quote") {
|
||||
{
|
||||
ss::converter<ss::quote<'"'>, ss::escape<'\\'>> c;
|
||||
auto& s = c.splitter;
|
||||
auto vec = expect_unterminated_quote(s, R"("just\"some","ra\")");
|
||||
auto vec = expect_unterminated_quote(s, R"("just\"some","r\a\a\\\a\")");
|
||||
std::vector<std::string> expected{"just\"some"};
|
||||
auto w = words(vec);
|
||||
w.pop_back();
|
||||
CHECK(w == expected);
|
||||
{
|
||||
buff.data_[strlen(buff.data_) - c.splitter.escaped_] = '\0';
|
||||
auto new_line = buff.append(R"(n,dom",str\"ings)");
|
||||
vec = c.resplit(new_line, strlen(new_line));
|
||||
CHECK(s.valid());
|
||||
CHECK(!s.unterminated_quote());
|
||||
expected = {"just\"some", "ra\"n,dom", "str\"ings"};
|
||||
expected = {"just\"some", "raa\\a\"n,dom", "str\"ings"};
|
||||
CHECK(words(vec) == expected);
|
||||
}
|
||||
}
|
||||
@ -692,6 +716,7 @@ TEST_CASE("splitter test unterminated quote") {
|
||||
w.pop_back();
|
||||
CHECK(w == expected);
|
||||
{
|
||||
buff.data_[strlen(buff.data_) - c.splitter.escaped_] = '\0';
|
||||
auto new_line = buff.append(R"( n,dom" , strings )");
|
||||
vec = c.resplit(new_line, strlen(new_line));
|
||||
CHECK(s.valid());
|
||||
|
||||
Loading…
Reference in New Issue
Block a user