Skip to content

KF-25 add tests for TextDetector #42

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
SergiusTheBest merged 4 commits into from
Aug 13, 2025
Merged

KF-25 add tests for TextDetector #42

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ccb76c8
add tests for TextDetector
Aug 11, 2025
21e8b3c
refactoring
Aug 12, 2025
dd8cfc9
add more tests
Aug 13, 2025
f91e853
Merge branch 'main' into KF-25-test-TextDetector
SergiusTheBest Aug 13, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions include/kf/TextDetector.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,10 @@ namespace kf
{
using namespace std;

///////////////////////////////////////////////////////////////////////////////////////////////////
// TextDetector class provides a utility to determine whether a given buffer contains textual data.
// It filters out control characters (except for \t, \n, \r) to verify that the content represents valid text.
// Supported encodings include ANSI, UTF-8, UTF-16 (LE/BE), and UTF-32 (LE/BE).
class TextDetector
{
public:
Expand Down
1 change: 1 addition & 0 deletions test/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,7 @@ wdk_add_driver(kf-test WINVER NTDDI_WIN10 STL
HexTest.cpp
MapTest.cpp
Vector.cpp
TextDetectorTest.cpp
ScopeExitTest.cpp
SingletonTest.cpp
DoubleLinkedListTest.cpp
Expand Down
221 changes: 221 additions & 0 deletions test/TextDetectorTest.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,221 @@
#include "pch.h"
#include <kf/TextDetector.h>

SCENARIO("TextDetector::isText")
{
GIVEN("Valid UTF-8 text with BOM")
{
constexpr uint8_t kData[] = { 0xEF, 0xBB, 0xBF, 'T', 'e', 's', 't' };

THEN("Text is detected")
{
REQUIRE(kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("UTF-8 text with BOM and invalid char")
{
constexpr uint8_t kData[] = { 0xEF, 0xBB, 0xBF, 0x01, 'a', 'b' };

THEN("Not a text is detected")
{
REQUIRE(!kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("Valid UTF-16LE text with BOM")
{
constexpr uint8_t kData[] = {
0xFF, 0xFE,
'T', 0x00,
'e', 0x00,
's', 0x00,
't', 0x00
};

THEN("Text is detected")
{
REQUIRE(kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
}

GIVEN("UTF-16LE text with BOM and invalid char")
{
constexpr uint8_t kData[] = {
0xFF, 0xFE,
0x01, 0x00, // invalid char
'a', 0x00
};

THEN("Not a text is detected")
{
REQUIRE(!kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("UTF-16BE text with BOM")
{
constexpr uint8_t kData[] = {
0xFE, 0xFF,
0x00, 'T',
0x00, 'e',
0x00, 's',
0x00, 't'
};

THEN("Text is detected")
{
REQUIRE(kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("UTF-16BE text with BOM and invalid char")
{
constexpr uint8_t kData[] = {
0xFE, 0xFF,
0x00, 0x01, // invalid char
0x00, 'a'
};

THEN("Not a text is detected")
{
REQUIRE(!kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("Valid UTF-32LE text with BOM")
{
constexpr uint8_t kData[] = {
0xFF, 0xFE, 0x00, 0x00,
'T', 0x00, 0x00, 0x00,
'e', 0x00, 0x00, 0x00,
's', 0x00, 0x00, 0x00,
't', 0x00, 0x00, 0x00
};

THEN("Text is detected")
{
REQUIRE(kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
}

GIVEN("UTF-32LE text with BOM and invalid char")
{
constexpr uint8_t kData[] = {
0xFF, 0xFE, 0x00, 0x00,
0x01, 0x00, 0x00, 0x00, // invalid char
'a', 0x00, 0x00, 0x00
};

THEN("Not a text is detected")
{
REQUIRE(!kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
}

GIVEN("Valid UTF-32BE text with BOM")
{
constexpr uint8_t kData[] = {
0x00, 0x00, 0xFE, 0xFF,
0x00, 0x00, 0x00, 'T',
0x00, 0x00, 0x00, 'e',
0x00, 0x00, 0x00, 's',
0x00, 0x00, 0x00, 't'
};

THEN("Text is detected")
{
REQUIRE(kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
}

GIVEN("UTF-32BE text with BOM and invalid char")
{
constexpr uint8_t kData[] = {
0x00, 0x00, 0xFE, 0xFF,
0x00, 0x00, 0x00, 0x01, // invalid char
0x00, 0x00, 0x00, 'a'
};

THEN("Not a text is detected")
{
REQUIRE(!kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
}

GIVEN("Valid UTF-16BE text without BOM")
{
constexpr uint8_t kData[] = {
0x00, 'T',
0x00, 'e',
0x00, 's',
0x00, 't'
};

THEN("Text is detected")
{
REQUIRE(kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("UTF-16BE text without BOM and invalid char")
{
constexpr uint8_t kData[] = {
0x00, 0x01, // invalid char
0x00, 'a'
};

THEN("Not a text is detected")
{
REQUIRE(!kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("Valid UTF-16LE text without BOM")
{
constexpr uint8_t kData[] = {
'T', 0x00,
'e', 0x00,
's', 0x00,
't', 0x00
};

THEN("Text is detected")
{
REQUIRE(kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
}

GIVEN("UTF-16LE text without BOM and invalid char")
{
constexpr uint8_t kData[] = {
0x01, 0x00, // invalid char
'a', 0x00
};

THEN("Not a text is detected")
{
REQUIRE(!kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("Valid UTF-8 text without BOM")
{
constexpr uint8_t kData[] = { 'T', 'e', 's', 't' };

THEN("Text is detected")
{
REQUIRE(kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};

GIVEN("UTF-8 text without BOM and invalid char")
{
constexpr uint8_t kData[] = { 0x01, 'a', 'b' };

THEN("Not a text is detected")
{
REQUIRE(!kf::TextDetector::isText(std::as_bytes(std::span{ kData })));
}
};
}