more tweaks to rationalize SLiM output formats

Author: bhaller

core/haplosome.cpp

@@ -1298,7 +1298,7 @@ EidosValue_SP Haplosome::ExecuteMethod_sumOfMutationsOfType(EidosGlobalStringID
 }
 
 // print the sample represented by haplosomes, using SLiM's own format
-void Haplosome::PrintHaplosomes_SLiM(std::ostream &p_out, std::vector<Haplosome *> &p_haplosomes, const Chromosome &p_chromosome, slim_objectid_t p_source_subpop_id)
+void Haplosome::PrintHaplosomes_SLiM(std::ostream &p_out, std::vector<Haplosome *> &p_haplosomes, const Chromosome &p_chromosome)
 {
 	Mutation *mut_block_ptr = gSLiM_Mutation_Block;
 	slim_popsize_t sample_size = (slim_popsize_t)p_haplosomes.size();
@@ -1334,14 +1334,29 @@ void Haplosome::PrintHaplosomes_SLiM(std::ostream &p_out, std::vector<Haplosome
 	// print the sample's haplosomes
 	p_out << "Haplosomes:" << std::endl;
 
-	for (slim_popsize_t j = 0; j < sample_size; j++)														// go through all individuals
+	for (slim_popsize_t j = 0; j < sample_size; j++)														// go through all haplosomes
 	{
 		Haplosome &haplosome = *p_haplosomes[j];
+		Individual *individual = haplosome.individual_;
 
-		if (p_source_subpop_id == -1)
-			p_out << "p*:" << j;
-		else
-			p_out << "p" << p_source_subpop_id << ":" << j;
+		if (!individual)
+			EIDOS_TERMINATION << "ERROR (Haplosome::PrintHaplosomes_SLiM): (internal error) missing individual for haplosome." << EidosTerminate();
+		
+		slim_popsize_t index = individual->index_;
+		
+		if (index == -1)
+			EIDOS_TERMINATION << "ERROR (Haplosome::PrintHaplosomes_SLiM): haplosomes being output must be visible in a subpopulation (i.e., may not belong to new juveniles)." << EidosTerminate();
+		
+		Subpopulation *subpop = individual->subpopulation_;
+		
+		if (!subpop)
+			EIDOS_TERMINATION << "ERROR (Haplosome::PrintHaplosomes_SLiM): (internal error) missing subpopulation for individual." << EidosTerminate();
+		
+		// BCH 2/9/2025: For SLiM 5, we now print the subpopulation id and the
+		// individual index for the haplosome, telling the user where each
+		// haplosome came from; probably not useful, but more useful than before
+		p_out << 'p' << subpop->subpopulation_id_;
+		p_out << ":i" << index;
 
 		for (int run_index = 0; run_index < haplosome.mutrun_count_; ++run_index)
 		{
@@ -3089,7 +3104,7 @@ EidosValue_SP Haplosome_Class::ExecuteMethod_outputX(EidosGlobalStringID p_metho
 
 		// Call out to print the actual sample
 		if (p_method_id == gID_output)
-			Haplosome::PrintHaplosomes_SLiM(output_stream, haplosomes, *chromosome, -1);	// -1 represents unknown source subpopulation
+			Haplosome::PrintHaplosomes_SLiM(output_stream, haplosomes, *chromosome);
 		else if (p_method_id == gID_outputMS)
 			Haplosome::PrintHaplosomes_MS(output_stream, haplosomes, *chromosome, filter_monomorphic);
 		else if (p_method_id == gID_outputVCF)
@@ -3124,7 +3139,7 @@ EidosValue_SP Haplosome_Class::ExecuteMethod_outputX(EidosGlobalStringID p_metho
 
 					outfile << " " << outfile_path << std::endl;
 
-					Haplosome::PrintHaplosomes_SLiM(outfile, haplosomes, *chromosome, -1);	// -1 represents unknown source subpopulation
+					Haplosome::PrintHaplosomes_SLiM(outfile, haplosomes, *chromosome);
 					break;
 				case gID_outputMS:
 					Haplosome::PrintHaplosomes_MS(outfile, haplosomes, *chromosome, filter_monomorphic);

core/haplosome.h

@@ -401,7 +401,7 @@ class Haplosome : public EidosObject
 	void record_derived_states(Species *p_species) const;
 
 	// print the sample represented by haplosomes, using SLiM's own format
-	static void PrintHaplosomes_SLiM(std::ostream &p_out, std::vector<Haplosome *> &p_haplosomes, const Chromosome &p_chromosome, slim_objectid_t p_source_subpop_id);
+	static void PrintHaplosomes_SLiM(std::ostream &p_out, std::vector<Haplosome *> &p_haplosomes, const Chromosome &p_chromosome);
 
 	// print the sample represented by haplosomes, using "ms" format
 	static void PrintHaplosomes_MS(std::ostream &p_out, std::vector<Haplosome *> &p_haplosomes, const Chromosome &p_chromosome, bool p_filter_monomorphic);

core/population.cpp

@@ -7845,7 +7845,9 @@ void Population::PrintAll(std::ostream &p_out, bool p_output_spatial_positions,
 
 					// i used to be the haplosome index, now it is the individual index; we will have one or
 					// two lines with this individual index, depending on the intrinsic ploidy of the chromosome
-					p_out << "p" << subpop_id << ":" << individual_index;
+					// since we changed from a haplosome index to an individual index, we now emit an "i",
+					// just follow the same convention as the Individuals section
+					p_out << "p" << subpop_id << ":i" << individual_index;
 
 					if (haplosome->IsNull())
 					{
@@ -8393,7 +8395,7 @@ void Population::PrintSample_SLiM(std::ostream &p_out, Subpopulation &p_subpop,
 	}
 
 	// print the sample using Haplosome's static member function
-	Haplosome::PrintHaplosomes_SLiM(p_out, sample, p_chromosome, p_subpop.subpopulation_id_);
+	Haplosome::PrintHaplosomes_SLiM(p_out, sample, p_chromosome);
 }
 
 // print sample of p_sample_size haplosomes from subpopulation p_subpop_id, using "ms" format

core/species.cpp

@@ -965,7 +965,11 @@ slim_tick_t Species::_InitializePopulationFromTextFile(const char *p_file, Eidos
 			std::istringstream iss(line);
 
 			iss >> sub;		// pX:iY – individual identifier
-			int pos = static_cast<int>(sub.find_first_of(':'));
+			std::size_t pos = static_cast<int>(sub.find_first_of(':'));
+			
+			if (pos == std::string::npos)
+				EIDOS_TERMINATION << "ERROR (Species::_InitializePopulationFromTextFile): colon missing in individual specifier." << EidosTerminate();
+			
 			std::string &&subpop_id_string = sub.substr(0, pos);
 
 			slim_objectid_t subpop_id = SLiMEidosScript::ExtractIDFromStringWithPrefix(subpop_id_string, 'p', nullptr);
@@ -1369,23 +1373,30 @@ slim_tick_t Species::_InitializePopulationFromTextFile(const char *p_file, Eidos
 			std::istringstream iss(line);
 
 			iss >> sub;
-			int pos = static_cast<int>(sub.find_first_of(':'));
+			std::size_t pos = static_cast<int>(sub.find_first_of(':'));
+			
+			if (pos == std::string::npos)
+				EIDOS_TERMINATION << "ERROR (Species::_InitializePopulationFromTextFile): colon missing in individual specifier." << EidosTerminate();
+			
 			std::string &&subpop_id_string = sub.substr(0, pos);
+			
 			slim_objectid_t subpop_id = SLiMEidosScript::ExtractIDFromStringWithPrefix(subpop_id_string, 'p', nullptr);
+			std::string &&individual_index_string = sub.substr(pos + 1, std::string::npos);
+			
+			if (individual_index_string[0] != 'i')
+				EIDOS_TERMINATION << "ERROR (Species::_InitializePopulationFromTextFile): reference to individual is malformed." << EidosTerminate();
+			
+			// this used to be the haplosome index, now it is the individual index and we have to figure out the haplosome index
+			int64_t individual_index_long = EidosInterpreter::NonnegativeIntegerForString(individual_index_string.c_str() + 1, nullptr);
 
 			Subpopulation *subpop = SubpopulationWithID(subpop_id);
 
 			if (!subpop)
 				EIDOS_TERMINATION << "ERROR (Species::_InitializePopulationFromTextFile): referenced subpopulation p" << subpop_id << " not defined." << EidosTerminate();
 
-			sub.erase(0, pos + 1);	// remove the subpop_id and the colon
-			
-			// this used to be the haplosome index, now it is the individual index and we have to figure out the haplosome index
-			int64_t individual_index_long = EidosInterpreter::NonnegativeIntegerForString(sub, nullptr);
-			
-			if ((individual_index_long < 0) || (individual_index_long > SLIM_MAX_SUBPOP_SIZE))
-				EIDOS_TERMINATION << "ERROR (Species::_InitializePopulationFromTextFile): individual index out of permitted range." << EidosTerminate();
-			slim_popsize_t individual_index = static_cast<slim_popsize_t>(individual_index_long);	// range-check is above since we need to check against SLIM_MAX_SUBPOP_SIZE
+			if (individual_index_long > subpop->parent_subpop_size_)
+				EIDOS_TERMINATION << "ERROR (Species::_InitializePopulationFromTextFile): referenced individual i" << individual_index_long << " is out of range." << EidosTerminate();
+			slim_popsize_t individual_index = static_cast<slim_popsize_t>(individual_index_long);
 
 			// detect when this is the second haplosome line for a given individual, and validate that
 			// FIXME this code is brittle in various ways -- a second line might be needed but omitted, or a third line might be given
@@ -1401,6 +1412,11 @@ slim_tick_t Species::_InitializePopulationFromTextFile(const char *p_file, Eidos
 			int haplosome_index = first_haplosome_index + is_individual_index_repeat;
 			Haplosome &haplosome = *(ind->haplosomes_[haplosome_index]);
 
+			std::cout << "for chromosome index " << (unsigned int)chromosome_index << " individual identifier " << sub << " parsed to subpop id " << subpop_id << " and individual index " << individual_index << ", is_individual_index_repeat == " << is_individual_index_repeat << ", haplosome_index " << haplosome_index << std::endl;
+			
+			if (haplosome.chromosome_index_ != chromosome->index_)
+				EIDOS_TERMINATION << "ERROR (Species::_InitializePopulationFromTextFile): (internal error) haplosome does not belong to the focal chromosome." << EidosTerminate();
+			
 			if (iss >> sub)
 			{
 				// BCH 2/5/2025: We instantiate null haplosomes only where expect them to be, based upon
@@ -1468,6 +1484,8 @@ slim_tick_t Species::_InitializePopulationFromTextFile(const char *p_file, Eidos
 					current_mutrun = haplosome.WillModifyRun_UNSHARED(current_mutrun_index, mutrun_context);
 				}
 
+				std::cout << "   adding mutation with identifier " << sub << ", mutation ID " << mutation << ", existing count " << current_mutrun->size() << std::endl;
+				
 				current_mutrun->emplace_back(mutation);
 			}
 			while (iss >> sub);