TEST_F(MHTMLTest, TestMHTMLEncoding)
{
addTestResources();
RefPtr<SharedBuffer> data = serialize("Test Serialization", "text/html", MHTMLArchive::UseDefaultEncoding);
// Read the MHTML data line per line and do some pseudo-parsing to make sure the right encoding is used for the different sections.
LineReader lineReader(std::string(data->data(), data->size()));
int sectionCheckedCount = 0;
const char* expectedEncoding = 0;
std::string line;
while (lineReader.getNextLine(&line)) {
if (line.compare(0, 13, "Content-Type:") == 0) {
ASSERT_FALSE(expectedEncoding);
if (line.find("multipart/related;") != std::string::npos) {
// Skip this one, it's part of the MHTML header.
continue;
}
if (line.find("text/") != std::string::npos)
expectedEncoding = "quoted-printable";
else if (line.find("image/") != std::string::npos)
expectedEncoding = "base64";
else
FAIL() << "Unexpected Content-Type: " << line;
continue;
}
if (line.compare(0, 26, "Content-Transfer-Encoding:") == 0) {
ASSERT_TRUE(expectedEncoding);
EXPECT_NE(line.find(expectedEncoding), std::string::npos);
expectedEncoding = 0;
sectionCheckedCount++;
}
}
EXPECT_EQ(12, sectionCheckedCount);
}
void Filters::Load()
{
status_t err;
// figure out where the file should be
BPath path;
err = find_directory(B_USER_SETTINGS_DIRECTORY, &path, true);
if (err != B_NO_ERROR)
return;
path.Append(FileNames::filtersFileName);
// open the file
BFile* file = new BFile(path.Path(), B_READ_ONLY);
if (file->InitCheck() != B_NO_ERROR) {
delete file;
return;
}
// load the text
off_t fileSize;
file->GetSize(&fileSize);
char* text = new char[fileSize];
file->ReadAt(0, text, fileSize);
delete file;
// parse it
TextReader reader(string_slice(text, text + fileSize));
FilterGroup* curGroup = NULL;
while (!reader.AtEOF()) {
// get the groupName
string_slice groupName = reader.NextTabField();
if (groupName.length() > 0) {
curGroup = GetFilterGroup(groupName);
if (curGroup == NULL) {
curGroup = new FilterGroup(groupName);
AddFilterGroup(curGroup);
}
reader.NextLine();
}
// if none, this is a filter line (if it's not blank)
else {
string_slice filterLine = reader.NextLine();
if (filterLine.length() > 0 && curGroup != NULL) {
Filter* filter = new Filter();
TextReader lineReader(filterLine);
filter->ReadFrom(&lineReader);
curGroup->AddFilter(filter);
}
}
}
// clean up
delete text;
}
bool CBasicFastaWrapper::ReadFile(CNcbiIstream& iStream)
{
bool result = (iStream.good());
if (!result) {
m_error = "Read Error: invalid stream.\n";
} else {
CNcbiOstrstream oss;
oss << iStream.rdbuf();
iStream.seekg(0);
m_activeFastaString = CNcbiOstrstreamToString(oss);
if (m_cacheRawFasta) m_rawFastaString = m_activeFastaString;
// temporarily turn off warning messages (in case of '.' in *.a2m files)
EDiagSev originalDiagSev = SetDiagPostLevel(eDiag_Error);
try{
CStreamLineReader lineReader(iStream);
CFastaReader fastaReader(lineReader, m_readFastaFlags);
//CCounterManager counterMgr(reader.SetIDGenerator(), NULL);
m_seqEntry = fastaReader.ReadSet();
// If there is only one sequence in the fasta, the Seq-entry returned is a Bioseq and not a Bioseq-set.
// In that case, change the Bioseq to a Bioseq-set so caller doesn't have to manage multiple Seq-entry choices.
if (m_seqEntry->IsSeq() && m_useBioseqSet) {
CRef<CSeq_entry> bioseqFromFasta(new CSeq_entry);
bioseqFromFasta->Assign(*m_seqEntry);
m_seqEntry->Select(CSeq_entry::e_Set);
m_seqEntry->SetSet().SetSeq_set().push_back(bioseqFromFasta);
}
} catch (...) {
result = false;
m_seqEntry.Reset();
}
if (m_seqEntry.Empty()) {
result = false;
m_error = "Read Error: empty seq entry.\n";
}
SetDiagPostLevel(originalDiagSev);
}
return result;
}
TEST_F(WebPageNewSerializeTest, TestMHTMLEncodingWithMorphingDataURL)
{
// Load a page with some data urls.
WebURL topFrameURL = toKURL(m_baseURL);
registerMockedURLLoad(topFrameURL, WebString::fromUTF8("page_with_morphing_data.html"), WebString::fromUTF8("pageserializer/"), htmlMimeType());
loadURLInTopFrame(topFrameURL);
WebCString mhtmlData = WebPageSerializer::serializeToMHTML(webView());
ASSERT_FALSE(mhtmlData.isEmpty());
// Read the MHTML data line and check that the string data:image is found
// exactly two times.
size_t nbDataURLs = 0;
LineReader lineReader(std::string(mhtmlData.data()));
std::string line;
while (lineReader.getNextLine(&line)) {
if (line.find("data:text") != std::string::npos)
nbDataURLs++;
}
EXPECT_EQ(2u, nbDataURLs);
}
int main(int argc, char **argv){
int size = 1000;
char *line = malloc(101);
int len;
HashTable *numbers;
FILE *fp = NULL;
numbers = createTable(size);
if(argc == 2){
fp = fopen(argv[1], "r");
}else if(argc > 2){
printf("error\n");
return -1;
}else if(argc < 2){
printf("error\n");
return -1;
}
if(fp == NULL){
printf("error\n");
return -1;
}
while(fgets(line, 100, fp) != NULL){
int i = lineReader(line, numbers);
if(i == -1){
return -1;
}
}
free(numbers->table);
free(numbers);
return 0;
}
