rewrite and refactor rred method to be able to handle even big (>30 MB)

patches (Closes: #554349) and hardening the method itself by using more
constants and a return value which can't be misinterpreted as linenumber

methods/rred.cc

@@ -1,3 +1,4 @@
+// Includes									/*{{{*/
 #include <apt-pkg/fileutl.h>
 #include <apt-pkg/error.h>
 #include <apt-pkg/acquire-method.h>
@@ -10,185 +11,205 @@
 #include <stdio.h>
 #include <errno.h>
 #include <apti18n.h>
-
-/* this method implements a patch functionality similar to "patch --ed" that is
- * used by the "tiffany" incremental packages download stuff. it differs from 
- * "ed" insofar that it is way more restricted (and therefore secure). in the
- * moment only the "c", "a" and "d" commands of ed are implemented (diff 
- * doesn't output any other). additionally the records must be reverse sorted 
- * by line number and may not overlap (diff *seems* to produce this kind of 
- * output). 
+										/*}}}*/
+/** \brief RredMethod - ed-style incremential patch method			{{{
+ *
+ *  This method implements a patch functionality similar to "patch --ed" that is
+ *  used by the "tiffany" incremental packages download stuff. It differs from
+ *  "ed" insofar that it is way more restricted (and therefore secure).
+ *  The currently supported ed commands are "<em>c</em>hange", "<em>a</em>dd" and
+ *  "<em>d</em>elete" (diff doesn't output any other).
+ *  Additionally the records must be reverse sorted by line number and
+ *  may not overlap (diff *seems* to produce this kind of output).
  * */
+class RredMethod : public pkgAcqMethod {
+	bool Debug;
+	// the size of this doesn't really matter (except for performance)
+	const static int BUF_SIZE = 1024;
+	// the supported ed commands
+	enum Mode {MODE_CHANGED='c', MODE_DELETED='d', MODE_ADDED='a'};
+	// return values
+	enum State {ED_OK=0, ED_ORDERING=1, ED_PARSER=2, ED_FAILURE=3};
 
-const char *Prog;
+	State applyFile(FILE *ed_cmds, FILE *in_file, FILE *out_file,
+	             unsigned long &line, char *buffer, Hashes *hash) const;
+	void ignoreLineInFile(FILE *fin, char *buffer) const;
+	void copyLineFromFileToFile(FILE *fin, FILE *fout,
+	                            Hashes *hash, char *buffer) const;
 
-class RredMethod : public pkgAcqMethod
-{
-   bool Debug;
-   // the size of this doesn't really matter (except for performance)    
-   const static int BUF_SIZE = 1024;
-   // the ed commands
-   enum Mode {MODE_CHANGED, MODE_DELETED, MODE_ADDED};
-   // return values
-   enum State {ED_OK, ED_ORDERING, ED_PARSER, ED_FAILURE};
-   // this applies a single hunk, it uses a tail recursion to 
-   // reverse the hunks in the file
-   int ed_rec(FILE *ed_cmds, FILE *in_file, FILE *out_file, int line, 
-      char *buffer, unsigned int bufsize, Hashes *hash);
-   // apply a patch file
-   int ed_file(FILE *ed_cmds, FILE *in_file, FILE *out_file, Hashes *hash);
+	State patchFile(FILE *ed_cmds, FILE *in_file, FILE *out_file, Hashes *hash) const;
 
 protected:
-   // the methods main method
-   virtual bool Fetch(FetchItem *Itm);
-   
-   public:
-   
-   RredMethod() : pkgAcqMethod("1.1",SingleInstance | SendConfig) {};
+	// the methods main method
+	virtual bool Fetch(FetchItem *Itm);
+
+public:
+	RredMethod() : pkgAcqMethod("1.1",SingleInstance | SendConfig) {};
 };
+										/*}}}*/
+/** \brief applyFile - in reverse order with a tail recursion			{{{
+ *
+ *  As it is expected that the commands are in reversed order in the patch file
+ *  we check in the first half if the command is valid, but doesn't execute it
+ *  and move a step deeper. After reaching the end of the file we apply the
+ *  patches in the correct order: last found command first.
+ *
+ *  \param ed_cmds patch file to apply
+ *  \param in_file base file we want to patch
+ *  \param out_file file to write the patched result to
+ *  \param line of command operation
+ *  \param buffer internal used read/write buffer
+ *  \param hash the created file for correctness
+ *  \return the success State of the ed command executor
+ */
+RredMethod::State RredMethod::applyFile(FILE *ed_cmds, FILE *in_file, FILE *out_file,
+			unsigned long &line, char *buffer, Hashes *hash) const {
+	// get the current command and parse it
+	if (fgets(buffer, BUF_SIZE, ed_cmds) == NULL) {
+		if (Debug == true)
+			std::clog << "rred: encounter end of file - we can start patching now.";
+		line = 0;
+		return ED_OK;
+	}
 
-int RredMethod::ed_rec(FILE *ed_cmds, FILE *in_file, FILE *out_file, int line, 
-      char *buffer, unsigned int bufsize, Hashes *hash) {
-   int pos;
-   int startline;
-   int stopline;
-   int mode;
-   int written;
-   char *idx;
+	// parse in the effected linenumbers
+	char* idx;
+	errno=0;
+	unsigned long const startline = strtol(buffer, &idx, 10);
+	if (errno == ERANGE || errno == EINVAL) {
+		_error->Errno("rred", "startline is an invalid number");
+		return ED_PARSER;
+	}
+	if (startline > line) {
+		_error->Error("rred: The start line (%lu) of the next command is higher than the last line (%lu). This is not allowed.", startline, line);
+		return ED_ORDERING;
+	}
+	unsigned long stopline;
+	if (*idx == ',') {
+		idx++;
+		errno=0;
+		stopline = strtol(idx, &idx, 10);
+		if (errno == ERANGE || errno == EINVAL) {
+			_error->Errno("rred", "stopline is an invalid number");
+			return ED_PARSER;
+		}
+	}
+	else {
+		stopline = startline;
+	}
+	line = startline;
 
-   /* get the current command and parse it*/
-   if (fgets(buffer, bufsize, ed_cmds) == NULL) {
-      return line;
-   }
-   startline = strtol(buffer, &idx, 10);
-   if (startline < line) {
-      return ED_ORDERING;
-   }
-   if (*idx == ',') {
-      idx++;
-      stopline = strtol(idx, &idx, 10);
-   }
-   else {
-      stopline = startline;
-   }
-   if (*idx == 'c') {
-      mode = MODE_CHANGED;
-	   if (Debug == true) {
-		   std::clog << "changing from line " << startline 
-			     << " to " << stopline << std::endl;
-	   }
-   }
-   else if (*idx == 'a') {
-      mode = MODE_ADDED;
-	   if (Debug == true) {
-		   std::clog << "adding after line " << startline << std::endl;
-	   }
-   }
-   else if (*idx == 'd') {
-      mode = MODE_DELETED;
-	   if (Debug == true) {
-		   std::clog << "deleting from line " << startline 
-			     <<  " to " << stopline << std::endl;
-	   }
-   }
-   else {
-      return ED_PARSER;
-   }
-   /* get the current position */
-   pos = ftell(ed_cmds);
-   /* if this is add or change then go to the next full stop */
-   if ((mode == MODE_CHANGED) || (mode == MODE_ADDED)) {
-      do {
-         fgets(buffer, bufsize, ed_cmds);
-         while ((strlen(buffer) == (bufsize - 1)) 
-               && (buffer[bufsize - 2] != '\n')) {
-            fgets(buffer, bufsize, ed_cmds);
-            buffer[0] = ' ';
-         }
-      } while (strncmp(buffer, ".", 1) != 0);
-   }
-   /* do the recursive call */
-   line = ed_rec(ed_cmds, in_file, out_file, line, buffer, bufsize, 
-         hash);
-   /* pass on errors */
-   if (line < 0) {
-      return line;
-   }
-   /* apply our hunk */
-   fseek(ed_cmds, pos, SEEK_SET); 
-   /* first wind to the current position */
-   if (mode != MODE_ADDED) {
-      startline -= 1;
-   }
-   while (line < startline) {
-      fgets(buffer, bufsize, in_file);
-      written = fwrite(buffer, 1, strlen(buffer), out_file);
-      hash->Add((unsigned char*)buffer, written);
-      while ((strlen(buffer) == (bufsize - 1)) 
-            && (buffer[bufsize - 2] != '\n')) {
-         fgets(buffer, bufsize, in_file);
-         written = fwrite(buffer, 1, strlen(buffer), out_file);
-         hash->Add((unsigned char*)buffer, written);
-      }
-      line++;
-   }
-   /* include from ed script */
-   if ((mode == MODE_ADDED) || (mode == MODE_CHANGED)) {
-      do {
-         fgets(buffer, bufsize, ed_cmds);
-         if (strncmp(buffer, ".", 1) != 0) {
-            written = fwrite(buffer, 1, strlen(buffer), out_file);
-            hash->Add((unsigned char*)buffer, written);
-            while ((strlen(buffer) == (bufsize - 1)) 
-                  && (buffer[bufsize - 2] != '\n')) {
-               fgets(buffer, bufsize, ed_cmds);
-               written = fwrite(buffer, 1, strlen(buffer), out_file);
-               hash->Add((unsigned char*)buffer, written);
-            }
-         }
-         else {
-            break;
-         }
-      } while (1);
-   }
-   /* ignore the corresponding number of lines from input */
-   if ((mode == MODE_DELETED) || (mode == MODE_CHANGED)) {
-      while (line < stopline) {
-         fgets(buffer, bufsize, in_file);
-         while ((strlen(buffer) == (bufsize - 1)) 
-               && (buffer[bufsize - 2] != '\n')) {
-            fgets(buffer, bufsize, in_file);
-         }
-         line++;
-      }
-   }
-   return line;
-}
+	// which command to execute on this line(s)?
+	switch (*idx) {
+		case MODE_CHANGED:
+			if (Debug == true)
+				std::clog << "Change from line " << startline << " to " << stopline << std::endl;
+			break;
+		case MODE_ADDED:
+			if (Debug == true)
+				std::clog << "Insert after line " << startline << std::endl;
+			break;
+		case MODE_DELETED:
+			if (Debug == true)
+				std::clog << "Delete from line " << startline << " to " << stopline << std::endl;
+			break;
+		default:
+			_error->Error("rred: Unknown ed command '%c'. Abort.", *idx);
+			return ED_PARSER;
+	}
+	unsigned char mode = *idx;
+
+	// save the current position
+	unsigned const long pos = ftell(ed_cmds);
+
+	// if this is add or change then go to the next full stop
+	if (mode == MODE_CHANGED || mode == MODE_ADDED) {
+		do
+			ignoreLineInFile(ed_cmds, buffer);
+		while (strncmp(buffer, ".", 1) != 0);
+	}
+
+	// do the recursive call - the last command is the one we need to execute at first
+	const State child = applyFile(ed_cmds, in_file, out_file, line, buffer, hash);
+	if (child != ED_OK) {
+		return child;
+	}
+
+	// change and delete are working on "line" - add is done after "line"
+	if (mode != MODE_ADDED)
+		line++;
+
+	// first wind to the current position and copy over all unchanged lines
+	while (line < startline) {
+		fgets(buffer, BUF_SIZE, in_file);
+		copyLineFromFileToFile(in_file, out_file, hash, buffer);
+		line++;
+	}
+
+	if (mode != MODE_ADDED)
+		line--;
 
-int RredMethod::ed_file(FILE *ed_cmds, FILE *in_file, FILE *out_file, 
-      Hashes *hash) {
+	// include data from ed script
+	if (mode == MODE_CHANGED || mode == MODE_ADDED) {
+		fseek(ed_cmds, pos, SEEK_SET);
+		while(fgets(buffer, BUF_SIZE, ed_cmds) != NULL) {
+			if (strncmp(buffer, ".", 1) != 0)
+				copyLineFromFileToFile(ed_cmds, out_file, hash, buffer);
+			else
+				break;
+		}
+	}
+
+	// ignore the corresponding number of lines from input
+	if (mode == MODE_CHANGED || mode == MODE_DELETED) {
+		while (line < stopline) {
+			ignoreLineInFile(in_file, buffer);
+			line++;
+		}
+	}
+	return ED_OK;
+}
+										/*}}}*/
+void RredMethod::copyLineFromFileToFile(FILE *fin, FILE *fout,			/*{{{*/
+					Hashes *hash, char *buffer) const {
+	size_t written = fwrite(buffer, 1, strlen(buffer), fout);
+	hash->Add((unsigned char*)buffer, written);
+	while (strlen(buffer) == (BUF_SIZE - 1) &&
+	       buffer[BUF_SIZE - 2] != '\n') {
+		fgets(buffer, BUF_SIZE, fin);
+		written = fwrite(buffer, 1, strlen(buffer), fout);
+		hash->Add((unsigned char*)buffer, written);
+	}
+}
+										/*}}}*/
+void RredMethod::ignoreLineInFile(FILE *fin, char *buffer) const {		/*{{{*/
+	fgets(buffer, BUF_SIZE, fin);
+	while (strlen(buffer) == (BUF_SIZE - 1) &&
+	       buffer[BUF_SIZE - 2] != '\n') {
+		fgets(buffer, BUF_SIZE, fin);
+		buffer[0] = ' ';
+	}
+}
+										/*}}}*/
+RredMethod::State RredMethod::patchFile(FILE *ed_cmds, FILE *in_file, FILE *out_file,		/*{{{*/
+      Hashes *hash) const {
    char buffer[BUF_SIZE];
-   int result;
-   int written;
    
    /* we do a tail recursion to read the commands in the right order */
-   result = ed_rec(ed_cmds, in_file, out_file, 0, buffer, BUF_SIZE, 
-         hash);
+   unsigned long line = -1; // assign highest possible value
+   State result = applyFile(ed_cmds, in_file, out_file, line, buffer, hash);
    
    /* read the rest from infile */
-   if (result >= 0) {
+   if (result == ED_OK) {
       while (fgets(buffer, BUF_SIZE, in_file) != NULL) {
-         written = fwrite(buffer, 1, strlen(buffer), out_file);
+         size_t const written = fwrite(buffer, 1, strlen(buffer), out_file);
          hash->Add((unsigned char*)buffer, written);
       }
    }
-   else {
-      return ED_FAILURE;
-   }
-   return ED_OK;
+   return result;
 }
-
-bool RredMethod::Fetch(FetchItem *Itm)
+										/*}}}*/
+bool RredMethod::Fetch(FetchItem *Itm)						/*{{{*/
 {
    Debug = _config->FindB("Debug::pkgAcquire::RRed", false);
    URI Get = Itm->Uri;
@@ -219,7 +240,7 @@ bool RredMethod::Fetch(FetchItem *Itm)
    FILE* fPatch = fdopen(Patch.Fd(), "r");
    FILE* fTo = fdopen(To.Fd(), "w");
    // now do the actual patching
-   if (ed_file(fPatch, fFrom, fTo, &Hash) != ED_OK) {
+   if (patchFile(fPatch, fFrom, fTo, &Hash) != ED_OK) {
      _error->Errno("rred", _("Could not patch file"));  
       return false;
    }
@@ -256,10 +277,8 @@ bool RredMethod::Fetch(FetchItem *Itm)
 
    return true;
 }
-
-/**
- * \brief Wrapper class for testing rred
- */
+										/*}}}*/
+/** \brief Wrapper class for testing rred */					/*{{{*/
 class TestRredMethod : public RredMethod {
 public:
 	/** \brief Run rred in debug test mode
@@ -276,9 +295,8 @@ public:
 		return Fetch(test);
 	}
 };
-
-/**
- *  \brief Starter for the rred method (or its test method)
+										/*}}}*/
+/** \brief Starter for the rred method (or its test method)			{{{
  *
  *  Used without parameters is the normal behavior for methods for
  *  the APT acquire system. While this works great for the acquire system
@@ -289,9 +307,6 @@ public:
  *  and will write the result to "Testfile.result".
  */
 int main(int argc, char *argv[]) {
-	Prog = strrchr(argv[0],'/');
-	Prog++;
-
 	if (argc == 0) {
 		RredMethod Mth;
 		return Mth.Run();
@@ -302,3 +317,4 @@ int main(int argc, char *argv[]) {
 		return result;
 	}
 }
+										/*}}}*/