int main(int argc, char *argv[]) {
const char input1[] = "I eat an apple.";
const char input2[] = "You drive a car.";
char buffer[BUFFER_SIZE];
rh_stack_instance disableBackReferenceStack;
rh_stackstack_instance sandbox;
rh_hashmap_instance backreference_lookup;
rh_list_instance warnings;
rh_stack_instance errors;
npeg_context context = {
&disableBackReferenceStack,
&sandbox,
&backreference_lookup,
&warnings,
&errors
};
npeg_inputiterator iterator;
npeg_astnode *ast, *subjnode, *verbnode, *objnode;
int (*parsetree)(npeg_inputiterator*, npeg_context*) = &sentence_root;
int IsMatch = 0;
// load npeg managed memory
npeg_inputiterator_constructor(&iterator, input1, strlen(input1));
npeg_constructor(&context, NULL);
printf("\tReached: parsetree(&iterator, &context) for input1.\n");
IsMatch = parsetree(&iterator, &context);
assert(IsMatch);
printf("\tVerified: The expected input was matched by parser.\n");
ast = npeg_get_ast(&context);
assert(0 == strcmp(ast->token->name, "Sentence"));
printf("\tVerified: The expected token name: %s.\n", ast->token->name);
assert(3 == ast->nof_children);
subjnode = ast->children[0];
verbnode = ast->children[1];
objnode = ast->children[2];
printf("\tVerified: #children of AST root.\n", ast->token->name);
assert(0 == strcmp(subjnode->token->name, "subject"));
printf("\tVerified: The expected token name: %s.\n", subjnode->token->name);
assert(0 == strcmp(verbnode->token->name, "verb"));
printf("\tVerified: The expected token name: %s.\n", verbnode->token->name);
assert(0 == strcmp(objnode->token->name, "object"));
printf("\tVerified: The expected token name: %s.\n", objnode->token->name);
npeg_inputiterator_get_text(buffer, &iterator, ast->token->start, ast->token->end);
assert(0 == strcmp(buffer, input1));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
npeg_destructor(&context);
npeg_inputiterator_destructor(&iterator);
npeg_astnode_delete_tree(ast, npeg_astnode_tokendeletion_callback);
// unload npeg managed memory
// load npeg managed memory
npeg_inputiterator_constructor(&iterator, input2, strlen(input2));
npeg_constructor(&context, NULL);
printf("\tReached: parsetree(&iterator, &context) for input2.\n");
IsMatch = parsetree(&iterator, &context);
assert(IsMatch);
printf("\tVerified: The expected input was matched by parser.\n");
ast = npeg_get_ast(&context);
assert(0 == strcmp(ast->token->name, "Sentence"));
printf("\tVerified: The expected token name: %s.\n", ast->token->name);
npeg_inputiterator_get_text(buffer, &iterator, ast->token->start, ast->token->end);
assert(0 == strcmp(buffer, input2));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
assert(3 == ast->nof_children);
subjnode = ast->children[0];
verbnode = ast->children[1];
objnode = ast->children[2];
printf("\tVerified: #children of AST root.\n", ast->token->name);
assert(0 == strcmp(subjnode->token->name, "subject"));
printf("\tVerified: The expected token name: %s.\n", subjnode->token->name);
assert(0 == strcmp(verbnode->token->name, "verb"));
printf("\tVerified: The expected token name: %s.\n", verbnode->token->name);
assert(0 == strcmp(objnode->token->name, "object"));
printf("\tVerified: The expected token name: %s.\n", objnode->token->name);
npeg_astnode_delete_tree(ast, npeg_astnode_tokendeletion_callback);
npeg_destructor(&context);
npeg_inputiterator_destructor(&iterator);
// unload npeg managed memory
return 0;
}
int main(int argc, char *argv[])
//argv[1] is Alphabet File,
//argv[2] is Datafile,
//argv[3] is maximum length of string
//argv[4] is the (optional) flag for changing the significance level
//argv[5] is multiline version, if used
// argv[6] is use of chi-squared test (optional)
{
int max_length;
char* data_file;
char* alpha_file;
HashTable2 *alphaHash;
bool isMulti = false;
bool stateRemoved = false; //dummy
Machine* machine;
double sigLevel = SIGLEVEL;
bool isSigLevel = false;
bool isChi = false;
//read in info from command line
//check for proper arguments
if(argc !=4 )
{
if (argc == 5)
FiveArgs(argv, isMulti, isSigLevel, sigLevel, isChi);
else if (argc == 6)
SixArgs(argv, isMulti, isSigLevel, sigLevel, isChi);
else if (argc == 7)
SevenArgs(argv, isMulti, isSigLevel, sigLevel, isChi);
else
PrintError();
}
PrintCopyrightInfo();
//set arguments
max_length = atoi(argv[3]);
data_file = argv[2];
alpha_file = argv[1];
//if no significance level is set, use default
//(should be set already, just to be careful)
if(!isSigLevel)
sigLevel = SIGLEVEL;
else
cout << "Significance level set to " << sigLevel <<".\n";
//create parse tree to store all strings in data
ParseTree parsetree(max_length);
//if using multi-line input, read in data and enter
//tree one line at a time
if(isMulti)
{
parsetree.ReadProcessMultiLine(alpha_file, data_file);
cout << "Multi-line option is set.\n"
<< "Max line length is "<< MAX_LINE_SIZE
<< "\n";
}
//otherwise do data read first, then enter in tree
else
{
//read in data and alphabet from files
parsetree.ReadInput(alpha_file, data_file);
//enter data in tree
parsetree.FillTree();
}
//make hash table of alpha symbols and indices
alphaHash = parsetree.MakeAlphaHash();
//create array of states
AllStates allstates(parsetree.getAlphaSize(), sigLevel, isChi);
//calculate frequency of occurence of symbols
allstates.InitialFrequencies(parsetree);
//check all possible strings up to max
//length and compare distributions
for(int k = 1; k <= max_length; k++)
allstates.CalcNewDist(k, parsetree);
//remove shorter strings
stateRemoved = allstates.DestroyShortHists(max_length, parsetree);
//remove all non-recurring states
allstates.CheckConnComponents(parsetree);
//check futures longer than 1,
//by using determinism of states
allstates.Determinize(parsetree);
//remove all non-recurring states (again, since there may be new ones)
allstates.CheckConnComponents(parsetree);
//store transitions from state to state
allstates.StoreTransitions(parsetree.getMaxLength(), parsetree.getAlpha());
//calculate distribution/frequency of states
allstates.GetStateDistsMulti(parsetree, data_file, alphaHash, isMulti);
//calculate information values
machine = new Machine(&allstates);
machine->CalcRelEnt(parsetree, alphaHash, isMulti);
machine->CalcRelEntRate(parsetree, alphaHash, isMulti);
machine->CalcCmu();
machine->CalcEntRate();
machine->CalcVariation(parsetree, alphaHash, isMulti);
//print out states
allstates.PrintOut(data_file, parsetree.getAlpha());
//print out machine and calculationsf
machine->PrintOut(data_file, alpha_file, data_file, max_length, sigLevel, isMulti, isChi, parsetree.getAlphaSize());
machine->PrintDot(data_file, parsetree.getAlpha());
delete machine;
return 1;
}
int main(int argc, char *argv[])
{
const char text1[] = "(1*3+4)/5*93";
const char text2[] = "9+(9-8)*10";
char buffer[BUFFER_SIZE];
rh_stack_instance disableBackReferenceStack;
rh_stackstack_instance sandbox;
rh_hashmap_instance backreference_lookup;
rh_list_instance warnings;
rh_stack_instance errors;
npeg_context context;
npeg_inputiterator iterator;
npeg_astnode* ast, *p_child;
int (*parsetree)(npeg_inputiterator*, npeg_context*) = &MathematicalFormula_impl_0;
int IsMatch = 0;
// load npeg managed memory
context.disableBackReferenceStack = &disableBackReferenceStack;
context.sandbox = &sandbox;
context.backReferenceLookup = &backreference_lookup;
context.warnings = &warnings;
context.errors = &errors;
npeg_inputiterator_constructor(&iterator, text1, strlen(text1));
npeg_constructor(&context, NULL);
IsMatch = parsetree(&iterator, &context);
assert(IsMatch);
printf("\tVerified: The expected input was matched by parser.\n");
ast = npeg_get_ast(&context);
npeg_printVisitor(ast, NULL);
assert(0 == strcmp(ast->token->name, "EXPRESSION"));
printf("\tVerified: The expected token name: '%s'.\n", ast->token->name);
npeg_inputiterator_get_text(buffer, &iterator, ast->token->start, ast->token->end);
assert(0 == strcmp(buffer, text1));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
assert(ast->nof_children == 5);
puts("\tVerified: Expected number of children.");
p_child = ast->children[0];
assert(0 == strcmp(p_child->token->name, "EXPRESSION"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "1*3+4"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[1];
assert(0 == strcmp(p_child->token->name, "SYMBOL"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "/"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[2];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "5"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[3];
assert(0 == strcmp(p_child->token->name, "SYMBOL"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "*"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[4];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "93"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
assert(ast->children[0]->nof_children == 5);
puts("\tVerified: Expected number of children.");
p_child = ast->children[0]->children[0];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "1"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[0]->children[1];
assert(0 == strcmp(p_child->token->name, "SYMBOL"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "*"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[0]->children[2];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "3"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[0]->children[3];
assert(0 == strcmp(p_child->token->name, "SYMBOL"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "+"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[0]->children[4];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "4"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
// unload npeg managed memory
npeg_astnode_delete_tree(ast, npeg_astnode_tokendeletion_callback);
npeg_destructor(&context);
npeg_inputiterator_destructor(&iterator);
npeg_inputiterator_constructor(&iterator, text2, strlen(text2));
npeg_constructor(&context, NULL);
IsMatch = parsetree(&iterator, &context);
assert(IsMatch);
printf("\tVerified: The expected input was matched by parser.\n");
ast = npeg_get_ast(&context);
assert(0 == strcmp(ast->token->name, "EXPRESSION"));
printf("\tVerified: The expected token name: '%s'.\n", ast->token->name);
npeg_inputiterator_get_text(buffer, &iterator, ast->token->start, ast->token->end);
assert(0 == strcmp(buffer, text2));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
assert(ast->nof_children == 5);
puts("\tVerified: Expected number of children.");
p_child = ast->children[0];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "9"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[1];
assert(0 == strcmp(p_child->token->name, "SYMBOL"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "+"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[2];
assert(0 == strcmp(p_child->token->name, "EXPRESSION"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "9-8"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[3];
assert(0 == strcmp(p_child->token->name, "SYMBOL"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "*"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[4];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "10"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
assert(ast->children[2]->nof_children == 3);
puts("\tVerified: Expected number of children.");
p_child = ast->children[2]->children[0];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "9"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[2]->children[1];
assert(0 == strcmp(p_child->token->name, "SYMBOL"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "-"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
p_child = ast->children[2]->children[2];
assert(0 == strcmp(p_child->token->name, "VALUE"));
printf("\tVerified: The expected token name: '%s'.\n", p_child->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "8"));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
// unload npeg managed memory
npeg_astnode_delete_tree(ast, npeg_astnode_tokendeletion_callback);
npeg_destructor(&context);
npeg_inputiterator_destructor(&iterator);
return 0;
}
int main(int argc, char *argv[])
{
char* input1 = "123-456-7890";
char buffer[BUFFER_SIZE];
rh_stack_instance disableBackReferenceStack;
rh_stackstack_instance sandbox;
rh_hashmap_instance backreference_lookup;
rh_list_instance warnings;
rh_stack_instance errors;
npeg_astnode *ast, *p_child;
npeg_context context;
npeg_inputiterator iterator;
int (*parsetree)(npeg_inputiterator*, npeg_context*) = &PhoneNumber_impl_0;
int IsMatch = 0;
// load npeg managed memory
context.disableBackReferenceStack = &disableBackReferenceStack;
context.sandbox = &sandbox;
context.backReferenceLookup = &backreference_lookup;
context.warnings = &warnings;
context.errors = &errors;
npeg_inputiterator_constructor(&iterator, input1, 31);
npeg_constructor(&context, NULL);
printf("\tReached: parsetree(&iterator, &context) for input1.\n");
IsMatch = parsetree(&iterator, &context);
assert(IsMatch);
printf("\tVerified: The expected input was matched by parser.\n");
ast = npeg_get_ast(&context);
npeg_printVisitor(ast, NULL);
assert(0 == strcmp(ast->token->name, "PhoneNumber"));
printf("\tVerified: The expected token name: %s.\n", ast->token->name);
npeg_inputiterator_get_text(buffer, &iterator, ast->token->start, ast->token->end);
assert(0 == strcmp(buffer, input1));
printf("\tVerified: The expected matched string: '%s'.\n", buffer);
assert(ast->nof_children == 3);
puts("\tVerified: Expected number of children.");
p_child = ast->children[0];
assert(0 == strcmp(p_child->token->name, "ThreeDigitCode"));
printf("\tVerified: The expected token name: %s.\n", ast->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "123"));
printf("\tVerified: The expected matched string of 1st child: '%s'.\n", buffer);
p_child = ast->children[1];
assert(0 == strcmp(p_child->token->name, "ThreeDigitCode"));
printf("\tVerified: The expected token name: %s.\n", ast->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "456"));
printf("\tVerified: The expected matched string of 2nd child: '%s'.\n", buffer);
p_child = ast->children[2];
assert(0 == strcmp(p_child->token->name, "FourDigitCode"));
printf("\tVerified: The expected token name: %s.\n", ast->token->name);
npeg_inputiterator_get_text(buffer, &iterator, p_child->token->start, p_child->token->end);
assert(0 == strcmp(buffer, "7890"));
printf("\tVerified: The expected matched string of 3rd child: '%s'.\n", buffer);
npeg_astnode_delete_tree(ast, npeg_astnode_tokendeletion_callback);
npeg_destructor(&context);
npeg_inputiterator_destructor(&iterator);
// unload npeg managed memory
return 0;
}
