encodingstest.cpp File Reference

#include "unittest.h"
#include "rapidjson/filereadstream.h"
#include "rapidjson/filewritestream.h"
#include "rapidjson/encodedstream.h"
#include "rapidjson/stringbuffer.h"

Include dependency graph for encodingstest.cpp:

Go to the source code of this file.

Macros
#define	UTF8_ACCEPT   0u

Functions
	TEST (EncodingsTest, UTF8)
	TEST (EncodingsTest, UTF16)
	TEST (EncodingsTest, UTF32)
	TEST (EncodingsTest, ASCII)

Macro Definition Documentation

UTF8_ACCEPT

#define UTF8_ACCEPT   0u

Definition at line 242 of file encodingstest.cpp.

Function Documentation

TEST() [1/4]

TEST	(	EncodingsTest	,
		ASCII	)

Definition at line 428 of file encodingstest.cpp.

                           {
    StringBuffer os, os2;
    for (unsigned codepoint = 0; codepoint < 128; codepoint++) {
        os.Clear();
        ASCII<>::Encode(os, codepoint);
        const ASCII<>::Ch* encodedStr = os.GetString();
        {
            StringStream is(encodedStr);
            unsigned decodedCodepoint;
            bool result = ASCII<>::Decode(is, &decodedCodepoint);
            if (!result || codepoint != decodedCodepoint)
                std::cout << std::hex << codepoint << " " << decodedCodepoint << std::endl;
        }
 
        // Validate
        {
            StringStream is(encodedStr);
            os2.Clear();
            bool result = ASCII<>::Validate(is, os2);
            EXPECT_TRUE(result);
            EXPECT_EQ(0, StrCmp(encodedStr, os2.GetString()));
        }
    }
}

Here is the call graph for this function:

TEST() [2/4]

TEST	(	EncodingsTest	,
		UTF16	)

Definition at line 337 of file encodingstest.cpp.

                           {
    GenericStringBuffer<UTF16<> > os, os2;
    GenericStringBuffer<UTF8<> > utf8os;
    for (const unsigned* range = kCodepointRanges; *range != 0xFFFFFFFF; range += 2) {
        for (unsigned codepoint = range[0]; codepoint <= range[1]; ++codepoint) {
            os.Clear();
            UTF16<>::Encode(os, codepoint);
            const UTF16<>::Ch* encodedStr = os.GetString();
 
            // Encode with Hoehrmann's code
            if (codepoint != 0) // cannot handle U+0000
            {
                // encode with UTF8<> first
                utf8os.Clear();
                UTF8<>::Encode(utf8os, codepoint);
 
                // transcode from UTF8 to UTF16 with Hoehrmann's code
                unsigned decodedCodepoint = 0;
                unsigned state = 0;
                UTF16<>::Ch buffer[3], *p = &buffer[0];
                for (const char* s = utf8os.GetString(); *s; ++s) {
                    if (!decode(&state, &decodedCodepoint, static_cast<unsigned char>(*s)))
                        break;
                }
 
                if (codepoint <= 0xFFFF)
                    *p++ = static_cast<UTF16<>::Ch>(decodedCodepoint);
                else {
                    // Encode code points above U+FFFF as surrogate pair.
                    *p++ = static_cast<UTF16<>::Ch>(0xD7C0 + (decodedCodepoint >> 10));
                    *p++ = static_cast<UTF16<>::Ch>(0xDC00 + (decodedCodepoint & 0x3FF));
                }
                *p++ = '\0';
 
                EXPECT_EQ(0, StrCmp(buffer, encodedStr));
            }
 
            // Decode
            {
                GenericStringStream<UTF16<> > is(encodedStr);
                unsigned decodedCodepoint;
                bool result = UTF16<>::Decode(is, &decodedCodepoint);
                EXPECT_TRUE(result);
                EXPECT_EQ(codepoint, decodedCodepoint);         
                if (!result || codepoint != decodedCodepoint)
                    std::cout << std::hex << codepoint << " " << decodedCodepoint << std::endl;
            }
 
            // Validate
            {
                GenericStringStream<UTF16<> > is(encodedStr);
                os2.Clear();
                bool result = UTF16<>::Validate(is, os2);
                EXPECT_TRUE(result);
                EXPECT_EQ(0, StrCmp(encodedStr, os2.GetString()));
            }
        }
    }
}

Here is the call graph for this function:

TEST() [3/4]

TEST	(	EncodingsTest	,
		UTF32	)

Definition at line 397 of file encodingstest.cpp.

                           {
    GenericStringBuffer<UTF32<> > os, os2;
    for (const unsigned* range = kCodepointRanges; *range != 0xFFFFFFFF; range += 2) {
        for (unsigned codepoint = range[0]; codepoint <= range[1]; ++codepoint) {
            os.Clear();
            UTF32<>::Encode(os, codepoint);
            const UTF32<>::Ch* encodedStr = os.GetString();
 
            // Decode
            {
                GenericStringStream<UTF32<> > is(encodedStr);
                unsigned decodedCodepoint;
                bool result = UTF32<>::Decode(is, &decodedCodepoint);
                EXPECT_TRUE(result);
                EXPECT_EQ(codepoint, decodedCodepoint);         
                if (!result || codepoint != decodedCodepoint)
                    std::cout << std::hex << codepoint << " " << decodedCodepoint << std::endl;
            }
 
            // Validate
            {
                GenericStringStream<UTF32<> > is(encodedStr);
                os2.Clear();
                bool result = UTF32<>::Validate(is, os2);
                EXPECT_TRUE(result);
                EXPECT_EQ(0, StrCmp(encodedStr, os2.GetString()));
            }
        }
    }
}

Here is the call graph for this function:

TEST() [4/4]

TEST	(	EncodingsTest	,
		UTF8	)

Definition at line 285 of file encodingstest.cpp.

                          {
    StringBuffer os, os2;
    for (const unsigned* range = kCodepointRanges; *range != 0xFFFFFFFF; range += 2) {
        for (unsigned codepoint = range[0]; codepoint <= range[1]; ++codepoint) {
            os.Clear();
            UTF8<>::Encode(os, codepoint);
            const char* encodedStr = os.GetString();
 
            // Decode with Hoehrmann
            {
                unsigned decodedCodepoint = 0;
                unsigned state = 0;
 
                unsigned decodedCount = 0;
                for (const char* s = encodedStr; *s; ++s)
                    if (!decode(&state, &decodedCodepoint, static_cast<unsigned char>(*s))) {
                        EXPECT_EQ(codepoint, decodedCodepoint);
                        decodedCount++;
                    }
 
                if (*encodedStr) {                  // This decoder cannot handle U+0000
                    EXPECT_EQ(1u, decodedCount);    // Should only contain one code point
                }
 
                EXPECT_EQ(UTF8_ACCEPT, state);
                if (UTF8_ACCEPT != state)
                    std::cout << std::hex << codepoint << " " << decodedCodepoint << std::endl;
            }
 
            // Decode
            {
                StringStream is(encodedStr);
                unsigned decodedCodepoint;
                bool result = UTF8<>::Decode(is, &decodedCodepoint);
                EXPECT_TRUE(result);
                EXPECT_EQ(codepoint, decodedCodepoint);
                if (!result || codepoint != decodedCodepoint)
                    std::cout << std::hex << codepoint << " " << decodedCodepoint << std::endl;
            }
 
            // Validate
            {
                StringStream is(encodedStr);
                os2.Clear();
                bool result = UTF8<>::Validate(is, os2);
                EXPECT_TRUE(result);
                EXPECT_EQ(0, StrCmp(encodedStr, os2.GetString()));
            }
        }
    }
}

Here is the call graph for this function: