I've got a huge PDF file with more than 100 pages and I want to separate them to single PDF files (containing only one page each). Problem is, that PoDoFo does not copy just the page, but the whole document because of the references (and so each of the 100 PDF files have same size as the 100-page PDF). A relevant mailing list post can be found, unfortunately there is no solution provided.
In source code of function InsertPages there is explanation:
This function works a bit different than one might expect.
Rather than copying one page at a time - we copy the ENTIRE document
and then delete the pages we aren't interested in.
We do this because
1) SIGNIFICANTLY simplifies the process
2) Guarantees that shared objects aren't copied multiple times
3) offers MUCH faster performance for the common cases
HOWEVER: because PoDoFo doesn't currently do any sort of "object
garbage collection" during a Write() - we will end up with larger
documents, since the data from unused pages will also be in there.
I have tried few methods to copy only relevant objects, but each of them failed.
Copy all pages and remove irrelevant ones
Use XObject wrapping: FillXObjectFromDocumentPage and FillXObjectFromExistingPage
Copy object by object
Use RenumberObjects with bDoGarbageCollection = true
but none of them worked out. Does anybody have an idea or working solution for this problem?
The only solution is to use another PDF library. Or wait for garbage collection to be implemented.
The problem is stated in the quote you mentioned:
> during a Write() - we will end up with larger documents, since the
> data from unused pages will also be in there.
This means podofo always puts the entire PDF content in your file, no matter what. The whole PDF is there, you just don't see parts of it.
Dennis from the podofo support sent me an working example of optimized version of InsertPages function which is actually fixing page references and decreases document size significantly!
void PdfMemDocument::InsertPages2(const PdfMemDocument & rDoc, std::vector<int> pageNumbers)
{
std::unordered_set<PdfObject*> totalSet;
std::vector<pdf_objnum> oldObjNumPages;
std::unordered_map<pdf_objnum, pdf_objnum> oldObjNumToNewObjNum;
std::vector<PdfObject*> newPageObjects;
// Collect all dependencies from all pages that are to be copied
for (int i = 0; i < pageNumbers.size(); ++i) {
PdfPage* page = rDoc.GetPage(pageNumbers[i]);
if (page) {
oldObjNumPages.push_back(page->GetObject()->Reference().ObjectNumber());
std::unordered_set<PdfObject*> *set = page->GetPageDependencies();
totalSet.insert(set->begin(), set->end());
delete set;
}
}
// Create a new page object for every copied page from the old document
// Copy all objects the pages depend on to the new document
for (auto it = totalSet.begin(); it != totalSet.end(); ++it) {
unsigned int length = static_cast<unsigned int>(GetObjects().GetSize() + GetObjects().GetFreeObjects().size());
PdfReference ref(static_cast<unsigned int>(length+1), 0);
PdfObject* pObj = new PdfObject(ref, *(*it));
pObj->SetOwner(&(GetObjects()));
if ((*it)->HasStream()) {
PdfStream *stream = (*it)->GetStream();
pdf_long length;
char* buf;
stream->GetCopy(&buf, &length);
PdfMemoryInputStream inputStream(buf, length);
pObj->GetStream()->SetRawData(&inputStream, length);
free(buf);
}
oldObjNumToNewObjNum.insert(std::pair<pdf_objnum, pdf_objnum>((*it)->Reference().ObjectNumber(), length+1));
GetObjects().push_back(pObj);
newPageObjects.push_back(pObj);
}
// In all copied objects, fix the object numbers so they are valid in the new document
for (auto it = newPageObjects.begin(); it != newPageObjects.end(); ++it) {
FixPageReferences(GetObjects(), *it, oldObjNumToNewObjNum);
}
// Insert the copied pages into the pages tree
for (auto it = oldObjNumPages.begin(); it != oldObjNumPages.end(); ++it) {
PdfObject* pageObject = GetObjects().GetObject(PdfReference(oldObjNumToNewObjNum[(*it)], 0));
PdfPage *page = new PdfPage(pageObject, std::deque<PdfObject*>());
GetPagesTree()->InsertPage(GetPageCount() - 1, page);
}
}
std::unordered_set<PdfObject *>* PdfPage::GetPageDependencies() const
{
std::unordered_set<PdfObject *> *set = new std::unordered_set<PdfObject *>();
const PdfObject* pageObj = GetObject();
if (pageObj) {
PdfVecObjects* objects = pageObj->GetOwner();
if (objects) {
set->insert((PdfObject*)pageObj);
objects->GetObjectDependencies2(pageObj, *set);
}
}
return set;
}
// Optimized version of PdfVecObjects::GetObjectDependencies
void PdfVecObjects::GetObjectDependencies2(const PdfObject* pObj, std::unordered_set<PdfObject*> &refMap) const
{
// Check objects referenced from this object
if (pObj->IsReference())
{
PdfObject* referencedObject = GetObject(pObj->GetReference());
if (referencedObject != NULL && refMap.count(referencedObject) < 1) {
(refMap).insert((PdfObject *)referencedObject); // Insert referenced object
GetObjectDependencies2((const PdfObject*)referencedObject, refMap);
}
}
else {
// Recursion
if (pObj->IsArray())
{
PdfArray::const_iterator itArray = pObj->GetArray().begin();
while (itArray != pObj->GetArray().end())
{
GetObjectDependencies2(&(*itArray), refMap);
++itArray;
}
}
else if (pObj->IsDictionary())
{
TCIKeyMap itKeys = pObj->GetDictionary().GetKeys().begin();
while (itKeys != pObj->GetDictionary().GetKeys().end())
{
if ((*itKeys).first != PdfName("Parent")) {
GetObjectDependencies2((*itKeys).second, refMap);
}
++itKeys;
}
}
}
}
void FixPageReferences(PdfVecObjects& objects, PdfObject* pObject, std::unordered_map<pdf_objnum, pdf_objnum>& oldNumToNewNum) {
if( !pObject)
{
PODOFO_RAISE_ERROR( ePdfError_InvalidHandle );
}
if( pObject->IsDictionary() )
{
TKeyMap::iterator it = pObject->GetDictionary().GetKeys().begin();
while( it != pObject->GetDictionary().GetKeys().end() )
{
if ((*it).first != PdfName("Parent")) {
FixPageReferences(objects, (*it).second, oldNumToNewNum);
}
++it;
}
}
else if( pObject->IsArray() )
{
PdfArray::iterator it = pObject->GetArray().begin();
while( it != pObject->GetArray().end() )
{
FixPageReferences(objects, &(*it), oldNumToNewNum),
++it;
}
}
else if( pObject->IsReference() )
{
//PdfObject* referencedObj = objects.GetObject(pObject->GetReference());
pdf_objnum oldnum = pObject->GetReference().ObjectNumber();
pdf_objnum newnum = oldNumToNewNum[oldnum];
if (!newnum) throw new std::exception("No new object number for old object number");
*pObject = PdfReference(newnum, 0);
}
}
Related
Hello i created a program to handle a config file line by checking each lines and get the config blocks but for first time i made it with php and the speed was amazing. we have some blocks like this
Block {
}
php program can read each line and detect about 50,000 of this blocks in just 1 second after that i went to c++ to create my program in c++ but i saw a very very bad problem. my program was too slow (read 50,000 of this blocks in 55 seconds) while my php codes was exactly the same of c++ codes (in action and activity). php was 55x faster than c++ while the codes are the same.
this is my code in php
const PATH = "conf.txt";
if(!file_exists(PATH)) die("path_not_found");
if(!is_readable((PATH))) die("path_not_readable");
$Lines = explode("\r\n", file_get_contents(PATH));
class Block
{
public $Name;
public $Keys = array();
public $Blocks = array();
}
function Handle(& $Lines, $Start, & $Return_block, & $End_on)
{
for ($i = $Start; $i < count($Lines); $i++)
{
while (trim($Lines[$i]) != "")
{
$Pos1 = strpos($Lines[$i], "{");
$Pos2 = strpos($Lines[$i], "}");
if($Pos1 !== false && ($Pos2 === false || $Pos2 > $Pos1)) // Detect { in less position
{
$thisBlock = new Block();
$thisBlock->Name = trim(substr($Lines[$i], 0, $Pos1));
$Lines[$i] = substr($Lines[$i], $Pos1 + 1);
Handle($Lines, $i, $thisBlock, $i);
$Return_block->Blocks[] = $thisBlock;
}
else { // Detect } in less position than {
$Lines[$i] = substr($Lines[$i], $Pos2 + 1);
$End_on = $i;
return;
}
}
}
}
$DefaultBlock = new Block();
Handle($Lines, 0, $DefaultBlock, $NullValue);
$OutsideKeys = $DefaultBlock->Keys;
$Blocks = $DefaultBlock->Blocks;
echo "Found (".count($OutsideKeys).") keys and (".count($Blocks).") blocks.<br><br>";
and this is my code in C++
string Trim(string & s)
{
auto wsfront = std::find_if_not(s.begin(), s.end(), [](int c) {return std::isspace(c); });
auto wsback = std::find_if_not(s.rbegin(), s.rend(), [](int c) {return std::isspace(c); }).base();
return (wsback <= wsfront ? std::string() : std::string(wsfront, wsback));
}
class Block
{
private:
string Name;
vector <Block> Blocks;
public:
void Add(Block & thisBlock) { Blocks.push_back(thisBlock); }
Block(string Getname = string()) { Name = Getname; }
int Count() { return Blocks.size(); }
};
void Handle(vector <string> & Lines, size_t Start, Block & Return, size_t & LastPoint, bool CheckEnd = true)
{
for (size_t i = Start; i < Lines.size(); i++)
{
while (Trim(Lines[i]) != "")
{
size_t Pos1 = Lines[i].find("{");
size_t Pos2 = Lines[i].find("}");
if (Pos1 != string::npos && (Pos2 == string::npos || Pos1 < Pos2)) // Found {
{
string Name = Trim(Lines[i].substr(0, Pos1));
Block newBlock = Block(Name);
Lines[i] = Lines[i].substr(Pos1 + 1);
Handle(Lines, i, newBlock, i);
Return.Add(newBlock);
}
else { // Found }
Lines[i] = Lines[i].substr(Pos2 + 1);
return;
}
}
}
}
int main()
{
string Cont;
___PATH::GetFileContent("D:\\conf.txt", Cont);
vector <string> Lines = ___String::StringSplit(Cont, "\r\n");
Block Return;
size_t Temp;
// The problem (low handle speed) start from here not from including or split
Handle(Lines, 0, Return, Temp);
cout << "Is(" << Return.Count() << ")" << endl;
return 0;
}
as you can see, this codes are exactly the same in action but i don't know why php handling in this code is 55x faster than my c++ codes. you can create a txt file and create about 50,000 of this block's
Block {
}
and test it yourself. please help me to fix this. i am really confused (same codes but not same performance
php = 50,000 blocks and detect in 1 second
c++ = 50,000 blocks and detect in 55 seconds (and maybe more) !
i have no problem in my program design. because i got my performance completely on php but my problem is on c++ that is 55x slower than php in same code action !
i am using (visual studio 2017) to compile this program (c++)
First, "code" is singular, not plural.
C++ is a very different language than php. It is not "the same code", and it is nowhere near the same in action.
For example, these two lines:
Block newBlock = Block(Name);
Return.Add(newBlock);
First create a Block on the stack, and then call Block's copy constructor to make another one inside the vector. You then throw away the stack object.
Also, vectors guarantee that they are contiguous, so as you add new Blocks via your Add method, vector will occasionally stop, allocate another chunk of memory (twice as big as the last one, iirc), copy everything over to that new chunk, and then free the old one. Either preallocate the vector (via vector::reserve()), or consider using something like a deque that doesn't guarantee continuity in memory if you don't need that property.
I also don't know what ___String::StringSplit does, but you are almost certain to have the same vector growth problem in reading your file.
Culprit is in these 2 lines:
Handle(Lines, i, newBlock, i);
Return.Add(newBlock);
Let's say you have 5 levels of 1 block each. What Happens on bottom one? You copy one instance of block. What happens on level 4? You copy 2 blocks (parent and its child). So for level 5 you make 15 copies - 1+2+3+4+5. Look at this diagram:
Handle level1 copies 5 blocks (`Return`->level4->level3->level4->level5)
Handle level2 copies 4 blocks (`Return`->level3->level4->level5)
Handle level3 copies 3 blocks (`Return`->level4->level5
Handle level4 copies 2 blocks (`Return`->level5)
Handle level5 copies 1 block (`Return`)
Formula is:
S = ( N + N^2 ) / 2
so for levels 20 you would do 210 copies and so on.
Suggestion is to use move semantics to avoid this copy:
// change method Add to this
void Add(Block thisBlock) { Blocks.push_back(std::move(thisBlock)); }
// and change this call
Return.Add( std::move( newBlock ) );
Or allocate blocks dynamically using smart pointers
Out of simple curiousity, try this Trim implementation instead:
void _Trim(std::string& result, const std::string& s) {
const auto* ptr = s.data();
const auto* left = ptr;
const auto* end = s.data() + s.size();
while (ptr < end && std::isspace(*ptr)) {
++ptr;
}
if (ptr == end) {
result = "";
return;
}
left = ptr;
while (end > left && std::isspace(*(end-1))) {
--end;
}
result = std::string(left, end);
}
std::string Trim(const std::string& s) {
// Not sure if RVO would fire for direct implementation of _Trim here
std::string result;
_Trim(result, s);
return result;
}
And another optimization:
void Add(Block& thisBlock) {
Blocks.push_back(std::move(thisBlock));
}
// Don't use thisBlock after call to this function. It is
// far from being pretty but it should avoid *lots* of copies.
I wonder if you'll get better result. Pls let me know.
I'm having some trouble with the following method and I need some help trying to figure out what I am doing wrong.
I want to return a reference to a Value in a document. I am passing the Document from outside the function so that when I read a json file into it I don't "lose it".
const rapidjson::Value& CTestManager::GetOperations(rapidjson::Document& document)
{
const Value Null(kObjectType);
if (m_Tests.empty())
return Null;
if (m_current > m_Tests.size() - 1)
return Null;
Test& the_test = m_Tests[m_current];
CMyFile fp(the_test.file.c_str()); // non-Windows use "r"
if (!fp.is_open())
return Null;
u32 operations_count = 0;
CFileBuffer json(fp);
FileReadStream is(fp.native_handle(), json, json.size());
if (document.ParseInsitu<kParseCommentsFlag>(json).HasParseError())
{
(...)
}
else
{
if (!document.IsObject())
{
(...)
}
else
{
auto tests = document.FindMember("td_tests");
if (tests != document.MemberEnd())
{
for (SizeType i = 0; i < tests->value.Size(); i++)
{
const Value& test = tests->value[i];
if (test["id"].GetInt() == the_test.id)
{
auto it = test.FindMember("operations");
if (it != test.MemberEnd())
{
//return it->value; is this legitimate?
return test["operations"];
}
return Null;
}
}
}
}
}
return Null;
}
Which I am calling like this:
Document document;
auto operations = TestManager().GetOperations(document);
When I inspect the value of test["operations"] inside the function I can see everything I would expect (debug code removed from the abode code).
When I inspect the returned value outside the function I can see that it's an array (which I expect). the member count int the array is correct as well, but when print it out, I only see garbage instead.
When I "print" the Value to a string inside the methods, I get what I expect (i.e. a well formated json), but when I do it outside all keys show up as "IIIIIIII" and values that aren't strings show up correctly.
rapidjson::StringBuffer strbuf2;
rapidjson::PrettyWriter<rapidjson::StringBuffer> writer2(strbuf2);
ops->Accept(writer2);
As this didn't work I decided to change the method to receive a Value as a parameter and do a deep copy into it like this
u32 CTestManager::GetOperationsEx(rapidjson::Document& document, rapidjson::Value& operations)
{
(...)
if (document.ParseInsitu<kParseCommentsFlag>(json).HasParseError())
{
(...)
}
else
{
if (!document.IsObject())
{
(...)
}
else
{
auto tests = document.FindMember("tests");
if (tests != document.MemberEnd())
{
for (SizeType i = 0; i < tests->value.Size(); i++)
{
const Value& test = tests->value[i];
if (test["id"].GetInt() == the_test.id)
{
const Value& opv = test["operations"];
Document::AllocatorType& allocator = document.GetAllocator();
operations.CopyFrom(opv, allocator); //would Swap work?
return operations.Size();
}
}
}
}
}
return 0;
}
Which I'm calling like this:
Document document;
Value operations(kObjectType);
u32 count = TestManager().GetOperationsEx(document, operations);
But... I get same thing!!!!
I know that it's going to be something silly but I can't put my hands on it!
Any ideas?
The problem in this case lies with the use of ParseInSitu. When any of the GetOperations exist the CFileBuffer loses scope and is cleaned up. Because the json is being parsed in-situ when the buffer to the file goes, so goes the data.
How to correct return created std::list through function argument? Now, I try so:
bool DatabaseHandler::tags(std::list<Tag> *tags)
{
QString sql = "SELECT * FROM " + Tag::TABLE_NAME + ";";
QSqlQueryModel model;
model.setQuery(sql);
if(model.lastError().type() != QSqlError::NoError) {
log(sql);
tags = NULL;
return false;
}
const int count = model.rowCount();
if(count > 0)
tags = new std::list<Tag>(count);
else
tags = new std::list<Tag>();
//some code
return true;
}
After I can use it:
std::list<Tag> tags;
mDB->tags(&tags);
Now, I fix my function:
bool DatabaseHandler::tags(std::list<Tag> **tags)
{
QString sql = "SELECT * FROM " + Tag::TABLE_NAME + ";";
QSqlQueryModel model;
model.setQuery(sql);
if(model.lastError().type() != QSqlError::NoError) {
log(sql);
*tags = NULL;
return false;
}
const int count = model.rowCount();
if(count > 0)
*tags = new std::list<Tag>(count);
else
*tags = new std::list<Tag>();
for(int i = 0; i < count; ++i) {
auto record = model.record(i);
Tag tag(record.value(Table::KEY_ID).toInt());
(*tags)->push_back(tag);
}
return true;
}
It works but list return size 4 although loop executes only 2 iterations and empty child objects (if I just called their default constructor). The Tag class hasn't copy constructor.
Since you passed an already instantiated list as a pointer to the function, there is no need to create another list.
In that sense, you question is pretty unclear. I'd suggest you read up a bit on pointers, references and function calls in general.
http://www.cplusplus.com/doc/tutorial/pointers/
http://www.cplusplus.com/doc/tutorial/functions/
UPDATE: I still strongly suggest you read up on the mentioned topics, since you don't know these fundamental points.
Anyway, this is what you probably want to do (event though I would suggest using references, here is the solution with pointers):
bool someFunc(std::list<Tag> **tags) {
// by default null the output argument
*tags = nullptr;
if (error) {
return false;
}
// dereference tags and assign it the address to a new instance of list<Tag>
*tags = new std::list<Tag>();
return true
}
std::list<Tag> *yourList;
if (someFunc(&yourList)) {
// then yourList is valid
} else {
// then you had an error and yourList == nullptr
}
However, this is not idiomatic C++. Please read a modern book or tutorial.
Use a reference.
bool DatabaseHandler::tags(std::list<Tag>& tags);
std::list<Tag> tags;
mDB->tags(tags);
You'll have to change all the -> to ., of course. Every operation done on the reference in the function will be done to the original tags list it was called with.
EDIT: If you want to create the list inside the function and return it, you have a couple options. The closest, I think, is to just return a list pointer, and return nullptr if the function fails.
//beware, pseudocode ahead
std::list<Tag>* DatabaseHandler::tags() //return new list
{
if (success)
return new std::list<Tag>(...); //construct with whatever
else
return nullptr; //null pointer return, didn't work
}
std::list<Tag> tags* = mDB->tags();
You could alternatively have it return an empty list instead, depending on how you want it to work. Taking a reference to a pointer would work the same way, too.
bool DatabaseHandler::tags(std::list<Tag>*&); //return true/false
std::list<Tag>* tags;
mDB->tags(tags); //tags will be set to point to a list if it worked
I am using jsoncpp to read settings from a JSON file.
I would like to have two cascading settings file, say MasterSettings.json and LocalSettings.json where LocalSettings is a subset of MasterSettings. I would like to load MasterSettings first and then LocalSettings. Where LocalSettings has a value that differs from MasterSettings, that value would overwrite the one from MasterSettings. Much like the cascade in CSS.
Is there any elegant way to do this with jsoncpp?
I'm going to assume your settings files are JSON objects.
As seen here, when JSONCpp parses a file, it clears the contents of the root node. This mean that trying to parse a new file on top of the old one won't preserve the old data. However, if you parse both files into separate Json::Value nodes, it's straight forward to recursively copy the values yourself by iterating over the keys in the second object using getMemberNames.
// Recursively copy the values of b into a. Both a and b must be objects.
void update(Json::Value& a, Json::Value& b) {
if (!a.isObject() || !b.isObject()) return;
for (const auto& key : b.getMemberNames()) {
if (a[key].isObject()) {
update(a[key], b[key]);
} else {
a[key] = b[key];
}
}
}
I know it has been a while. but...
In addition to the correct answer and the commentary, here is a code version for those who use a older g++ version:
void jsonMerge(Json::Value &a, Json::Value &b) {
if (!a.isObject() || !b.isObject()) return;
vector<string> member_name = b.getMemberNames();
string key = "";
for (unsigned i = 0, len = member_name.size(); i < len; i++) {
key = member_name[i];
if (!a[key].isNull() && a[key].type() == Json::objectValue && b[key].type() == Json::objectValue) {
jsonMerge(a[key], b[key]);
} else {
a[key] = b[key];
}
}
member_name.clear();
}
For some odd reason, my application likes to break on me when I switch to release and run it outside of my debugger. Here's what works for me, and here's what doesn't
(Qt Creator is the IDE)
Debugging with debug configuration - ok
Running with debug configuration - ok
Debugging with release configuration - ok
Running with release configuration - application crash
My UI is one project, and the core for some stuff as a separate dependency. On Windows (compiling with MSVCC), I hit a menu button, which eventually calls down to a function. In that function, the app breaks on adding a new element to a vector. e.g:
str *x = new str();
str *y = new str();
/* ...set some of x & y's members... */
vector.push_back(x); // works fine
vector.push_back(y); // causes crash
If I comment out the line vector.push_back(y);, the app continues no problem until the app leaves the event scope (i.e. the end of OnMenuButtonClick). On OS X, it's similar to the issue of adding an element to a vector, except I have:
std::vector<foo *> SomeFunction()
{
std::vector<foo *> returningVector;
/* do stuff */
std::vector<foo *> goo = GetFooObjects();
for (int i = 0; i < goo.size(); i++)
{
returningVector.push_back(goo[i]); // breaks here
}
}
So what are some causes of this strange behavior without a debugger attached and not under debug configuration? I've checked to make sure all of my variables are initialized, so I'm stumped. If you want to view the code above, the first part can be located here, and the second part here. Please forgive anything you see as "bad", and if you have suggestions that you just can't contain, then please do message me on GitHub.
Edit:
I looked more into it, and found out exactly what's causing the problem, but don't know how to fix it. This is the function where my app crashes (on OS X):
vector<Drive *> Drive::GetFATXDrives( bool HardDisks )
{
vector<Drive *> Return;
if (HardDisks)
{
vector<DISK_DRIVE_INFORMATION> Disks = GetPhysicalDisks();
for (int i = 0; i < (int)Disks.size(); i++)
{
DISK_DRIVE_INFORMATION ddi = Disks.at(i);
// First, try reading the disk way
Streams::xDeviceStream* DS = NULL;
try
{
char path[0x200] = {0};
wcstombs(path, ddi.Path, wcslen(ddi.Path));
DS = new Streams::xDeviceStream(ddi.Path);
}
catch (xException& e)
{
continue;
}
if (DS == NULL || DS->Length() == 0 || DS->Length() < HddOffsets::Data)
{
// Disk is not of valid length
continue;
}
DS->SetPosition(HddOffsets::Data);
// Read the FATX partition magic
int Magic = DS->ReadInt32();
// Close the stream
DS->Close();
// Compare the magic we read to the *actual* FATX magic
if (Magic == FatxMagic)
{
Drive *d = new Drive(Disks.at(i).Path, Disks.at(i).FriendlyName, false);
Return.push_back(d);
}
}
}
vector<Drive *> LogicalDisks = GetLogicalPartitions();
for (int i = 0; i < (int)LogicalDisks.size(); i++)
{
Return.push_back(LogicalDisks.at(i));
}
return Return;
}
If I change if (HardDisks) to if (HardDisks = false), the app works just fine. So, I looked into that scope and discovered that after vector<DISK_DRIVE_INFORMATION> Disks = GetPhysicalDisks();, the heap gets corrupt or something like that. I noticed this because in the debugger, after that function is called, my HardDisks bool changes to "false", which wasn't what it was before.
Here is GetPhysicalDisks:
vector<Drive::DISK_DRIVE_INFORMATION> Drive::GetPhysicalDisks( void )
{
// RIGHT AFTER this vector is initialized, everything goes to hell
vector<Drive::DISK_DRIVE_INFORMATION> ReturnVector;
DIR *dir;
dirent *ent;
dir = opendir("/dev/");
if (dir != NULL)
{
// Read the shit
while ((ent = readdir(dir)) != NULL)
{
// Check the directory name, and if it starts with "disk" then keep it!
QRegExp exp("disk*");
exp.setPatternSyntax(QRegExp::Wildcard);
exp.setCaseSensitivity(Qt::CaseInsensitive);
if (exp.exactMatch(ent->d_name))
{
DISK_DRIVE_INFORMATION curdir;
memset(curdir.FriendlyName, 0, sizeof(curdir.FriendlyName));
memset(curdir.Path, 0, sizeof(curdir.Path));
char diskPath[0x50] = {0};
sprintf(diskPath, "/dev/r%s", ent->d_name);
mbstowcs(curdir.Path, diskPath, strlen(diskPath));
int device;
if ((device = open(diskPath, O_RDONLY)) > 0)
{
#ifdef __linux
hd_driveid hd;
if (!ioctl(device, HDIO_GET_IDENTITY, &hd))
{
swprintf(curdir.FriendlyName, strlen(hd) * 2, L"%hs", hd.model);
}
#elif defined __APPLE__
mbstowcs(curdir.FriendlyName, ent->d_name, strlen(ent->d_name));
#endif
ReturnVector.push_back(curdir);
}
}
}
}
return ReturnVector;
}
While this isn't a real answer as to what happened, I did find a way to fix the problem. Looking at my edit above, I edited my Drive::GetFATXDrives function like so:
vector<Drive *> Drive::GetFATXDrives( bool HardDisks )
{
// Initialize Disks vector up here
vector<DISK_DRIVE_INFORMATION> Disks;
// Call the function to get the hard disks
if (HardDisks)
Drive::GetPhysicalDisks(Disks);
vector<Drive *> ReturnVector;
if (HardDisks)
{
Streams::xDeviceStream* DS = NULL;
for (int i = 0; i < (int)Disks.size(); i++)
{
/* ... */
}
if (DS)
{
DS->Close();
delete DS;
}
}
vector<Drive *> LogicalDisks = GetLogicalPartitions();
for (int i = 0; i < LogicalDisks.size(); i++)
{
ReturnVector.push_back(LogicalDisks[i]);
}
return ReturnVector;
}
And my Drive::GetPhysicalDisks function now takes a vector<DISK_DRIVE_INFORMATION> reference instead of returning one. Seemed to make my program work just fine after that.