Split parsing code into its own file and cleanup includes

5 files changed, 218 insertions, 200 deletions

diff --git a/main.cpp b/main.cpp
index a6963f1..7786149 100644
--- a/main.cpp
+++ b/main.cpp
@@ -2,15 +2,15 @@
 #include <fstream>
 #include <vector>
 #include <string>
-#include <unordered_map>
 #include <unistd.h>
 #include <cstdlib>
-#include <tuple>
-#include <cctype>
 #include <cassert>
 #include <sys/time.h>
+#include <cstring>
+
 #include "params.h"
 #include "world.h"
+#include "parse.h"
 
 #ifndef _WIN32
 # include <signal.h>
@@ -19,201 +19,6 @@
 using namespace std;
 
 
-void trim(string &str){
-	while(str.size()>0&&isspace(str[0]))str.erase(0,1);
-	while(str.size()>0&&isspace(str.back()))str.erase(str.size()-1,1);
-}
-
-void squashSpaces(string &str){
-	bool sp=false;
-	for(size_t i=0;i<str.size();i++){
-		if(isspace(str[i])){
-			if(sp){
-				str.erase(i,1);
-				i--;
-			} else {
-				str[i]=' ';
-				sp=true;
-			}
-		} else {
-			sp=false;
-		}
-	}
-}
-
-vector<string> splittrim(const string &str,char sep){
-	if(str.size()==0)return {};
-	vector<string> res;
-	size_t cursor=0;
-	while(true){
-		size_t idx=str.find(sep,cursor);
-		if(idx==string::npos){
-			string s=str.substr(cursor);
-			trim(s);
-			res.push_back(s);
-			return res;
-		}
-		string s=str.substr(cursor,idx-cursor);
-		trim(s);
-		res.push_back(s);
-		cursor=idx+1;
-	}
-}
-
-void lowercase(string &str){
-	for(size_t i=0;i<str.size();i++){
-		str[i]=tolower(str[i]);
-	}
-}
-
-Argument parseArgument(const string &str,const unordered_map<string,Location> &labels,Location ip){
-	if(str[0]=='#'||str[0]=='%'){
-		bool remote=str[0]=='%';
-		if(isdigit(str[1])){
-			int num=atoi(str.data()+1);
-			assert(num>=1&&num<=20);
-			return {arg_t::var,remote,num,{}};
-		} else {
-			return {arg_t::name,remote,0,str.substr(1)};
-		}
-	} else if(str[0]=='@'){
-		if(labels.find(str.substr(1))==labels.end()){
-			return {arg_t::undeflabel,false,0,str.substr(1)};
-		}
-		Location ref=labels.find(str.substr(1))->second;
-		assert(ref.bank==ip.bank);
-		return {arg_t::number,false,ref.pos-ip.pos,{}};
-	} else if(str[0]=='$'){
-		return {arg_t::constant,false,0,str.substr(1)};
-	} else if(isdigit(str[0])){
-		return {arg_t::number,false,atoi(str.data()),{}};
-	} else {
-		assert(false);
-	}
-}
-
-Team assemble(const string &source){
-	Team team;
-	unordered_map<string,Location> labels;
-
-	for(string line : splittrim(source,'\n')){
-		if(line.size()==0)continue;
-
-		string word1=line.substr(0,line.find(' '));
-		string word2r=line.find(' ')==string::npos?"":line.substr(line.find(' ')+1);
-		if(word1=="published"){
-			string word2=word2r.substr(0,word2r.find(' '));
-			string word3r=word2r.find(' ')==string::npos?"":word2r.substr(word2r.find(' ')+1);
-			if(word2=="name"){
-				team.name=word3r;
-			}
-		} else if(word1=="bank"){
-			team.banks.emplace_back();
-		} else if(word1[0]=='@'){
-			assert(line.find(' ')==string::npos);
-			assert(labels.find(word1.substr(1))==labels.end());
-			labels[word1.substr(1)]={(int)team.banks.size()-1,(int)team.banks.back().size()};
-		} else {
-			assert(team.banks.size()>0);
-			vector<string> args=splittrim(word2r,',');
-			vector<Argument> pargs;
-			for(const string &s : args){
-				pargs.push_back(parseArgument(s,labels,
-					{(int)team.banks.size()-1,(int)team.banks.back().size()}));
-			}
-			if(word1=="jump"||word1=="turn"||word1=="scan")assert(pargs.size()==1);
-			else if(word1=="die"||word1=="move")assert(pargs.size()==0);
-			else if(word1=="create")assert(pargs.size()==3);
-			else assert(pargs.size()==2);
-
-			Script &s=team.banks.back();
-			if(word1=="set")s.push_back(Instruction::make(ins_t::set,{pargs[0],pargs[1]}));
-			else if(word1=="add")s.push_back(Instruction::make(ins_t::add,{pargs[0],pargs[1]}));
-			else if(word1=="sub")s.push_back(Instruction::make(ins_t::sub,{pargs[0],pargs[1]}));
-			else if(word1=="comp")s.push_back(Instruction::make(ins_t::comp,{pargs[0],pargs[1]}));
-			else if(word1=="trans")s.push_back(Instruction::make(ins_t::trans,{pargs[0],pargs[1]}));
-			else if(word1=="jump")s.push_back(Instruction::make(ins_t::jump,{pargs[0]}));
-			else if(word1=="bjump")s.push_back(Instruction::make(ins_t::bjump,{pargs[0],pargs[1]}));
-			else if(word1=="die")s.push_back(Instruction::make(ins_t::die,{}));
-			else if(word1=="move")s.push_back(Instruction::make(ins_t::move,{}));
-			else if(word1=="turn")s.push_back(Instruction::make(ins_t::turn,{pargs[0]}));
-			else if(word1=="scan")s.push_back(Instruction::make(ins_t::scan,{pargs[0]}));
-			else if(word1=="create")s.push_back(Instruction::make(ins_t::create,{pargs[0],pargs[1],pargs[2]}));
-			else assert(false);
-		}
-	}
-
-	int bank=0;
-	for(Script &script : team.banks){
-		int pos=0;
-		for(Instruction &ins : script){
-			for(Argument &arg : ins.args){
-				if(arg.type==arg_t::undeflabel){
-					assert(labels.find(arg.name)!=labels.end());
-					assert(labels[arg.name].bank==bank);
-					arg.type=arg_t::number;
-					arg.num=labels[arg.name].pos-pos;
-				}
-			}
-			pos++;
-		}
-		bank++;
-	}
-
-	return team;
-}
-
-string preprocess(istream &file){
-	unordered_map<string,string> defines;
-
-	string result;
-
-	string line;
-	while(getline(file,line)){
-		if(line.find(';')!=string::npos){
-			line.erase(line.find(';'));
-		}
-		trim(line);
-		if(line.size()==0)continue;
-		squashSpaces(line);
-		lowercase(line);
-
-		string word1=line.substr(0,line.find(' '));
-		if(word1=="define"){
-			string word2r=line.find(' ')==string::npos?"":line.substr(line.find(' ')+1);
-			string word2=word2r.substr(0,word2r.find(' '));
-			string word3r=word2r.find(' ')==string::npos?"":word2r.substr(word2r.find(' ')+1);
-			assert(defines.find(word2.substr(1))==defines.end());
-			assert(word3r[0]=='{');
-			string value=word3r.substr(1);
-			assert(word3r.find('}')==string::npos||word3r.find('}')==word3r.size()-1);
-			if(word3r.back()!='}'){
-				while(true){
-					char c=file.get();
-					if(c=='}')break;
-					value+=c;
-				}
-				assert(file.get()=='\n');
-			} else {
-				value.erase(value.size()-1);
-			}
-			defines[word2.substr(1)]=value;
-		} else {
-			while(line.find('&')!=string::npos){
-				size_t start=line.find('&')+1;
-				size_t end=line.find_first_not_of("abcdefghijklmnopqrstuvwxyz0123456789._",start);
-				if(end==string::npos)end=line.size();
-				assert(defines.find(line.substr(start,end-start))!=defines.end());
-				line=line.substr(0,start-1)+defines.find(line.substr(start,end-start))->second+line.substr(end);
-			}
-			result+=line+'\n';
-		}
-	}
-
-	return result;
-}
-
-
 static ScreenBuffer *sb;
 
 #ifndef _WIN32
diff --git a/parse.cpp b/parse.cpp
new file mode 100644
index 0000000..a0267cc
--- /dev/null
+++ b/parse.cpp
@@ -0,0 +1,202 @@
+#include <fstream>
+#include <vector>
+#include <string>
+#include <unordered_map>
+#include <cctype>
+#include <cassert>
+
+#include "parse.h"
+
+void trim(string &str){
+	while(str.size()>0&&isspace(str[0]))str.erase(0,1);
+	while(str.size()>0&&isspace(str.back()))str.erase(str.size()-1,1);
+}
+
+void squashSpaces(string &str){
+	bool sp=false;
+	for(size_t i=0;i<str.size();i++){
+		if(isspace(str[i])){
+			if(sp){
+				str.erase(i,1);
+				i--;
+			} else {
+				str[i]=' ';
+				sp=true;
+			}
+		} else {
+			sp=false;
+		}
+	}
+}
+
+vector<string> splittrim(const string &str,char sep){
+	if(str.size()==0)return {};
+	vector<string> res;
+	size_t cursor=0;
+	while(true){
+		size_t idx=str.find(sep,cursor);
+		if(idx==string::npos){
+			string s=str.substr(cursor);
+			trim(s);
+			res.push_back(s);
+			return res;
+		}
+		string s=str.substr(cursor,idx-cursor);
+		trim(s);
+		res.push_back(s);
+		cursor=idx+1;
+	}
+}
+
+void lowercase(string &str){
+	for(size_t i=0;i<str.size();i++){
+		str[i]=tolower(str[i]);
+	}
+}
+
+Argument parseArgument(const string &str,const unordered_map<string,Location> &labels,Location ip){
+	if(str[0]=='#'||str[0]=='%'){
+		bool remote=str[0]=='%';
+		if(isdigit(str[1])){
+			int num=atoi(str.data()+1);
+			assert(num>=1&&num<=20);
+			return {arg_t::var,remote,num,{}};
+		} else {
+			return {arg_t::name,remote,0,str.substr(1)};
+		}
+	} else if(str[0]=='@'){
+		if(labels.find(str.substr(1))==labels.end()){
+			return {arg_t::undeflabel,false,0,str.substr(1)};
+		}
+		Location ref=labels.find(str.substr(1))->second;
+		assert(ref.bank==ip.bank);
+		return {arg_t::number,false,ref.pos-ip.pos,{}};
+	} else if(str[0]=='$'){
+		return {arg_t::constant,false,0,str.substr(1)};
+	} else if(isdigit(str[0])){
+		return {arg_t::number,false,atoi(str.data()),{}};
+	} else {
+		assert(false);
+	}
+}
+
+Team assemble(const string &source){
+	Team team;
+	unordered_map<string,Location> labels;
+
+	for(string line : splittrim(source,'\n')){
+		if(line.size()==0)continue;
+
+		string word1=line.substr(0,line.find(' '));
+		string word2r=line.find(' ')==string::npos?"":line.substr(line.find(' ')+1);
+		if(word1=="published"){
+			string word2=word2r.substr(0,word2r.find(' '));
+			string word3r=word2r.find(' ')==string::npos?"":word2r.substr(word2r.find(' ')+1);
+			if(word2=="name"){
+				team.name=word3r;
+			}
+		} else if(word1=="bank"){
+			team.banks.emplace_back();
+		} else if(word1[0]=='@'){
+			assert(line.find(' ')==string::npos);
+			assert(labels.find(word1.substr(1))==labels.end());
+			labels[word1.substr(1)]={(int)team.banks.size()-1,(int)team.banks.back().size()};
+		} else {
+			assert(team.banks.size()>0);
+			vector<string> args=splittrim(word2r,',');
+			vector<Argument> pargs;
+			for(const string &s : args){
+				pargs.push_back(parseArgument(s,labels,
+					{(int)team.banks.size()-1,(int)team.banks.back().size()}));
+			}
+			if(word1=="jump"||word1=="turn"||word1=="scan")assert(pargs.size()==1);
+			else if(word1=="die"||word1=="move")assert(pargs.size()==0);
+			else if(word1=="create")assert(pargs.size()==3);
+			else assert(pargs.size()==2);
+
+			Script &s=team.banks.back();
+			if(word1=="set")s.push_back(Instruction::make(ins_t::set,{pargs[0],pargs[1]}));
+			else if(word1=="add")s.push_back(Instruction::make(ins_t::add,{pargs[0],pargs[1]}));
+			else if(word1=="sub")s.push_back(Instruction::make(ins_t::sub,{pargs[0],pargs[1]}));
+			else if(word1=="comp")s.push_back(Instruction::make(ins_t::comp,{pargs[0],pargs[1]}));
+			else if(word1=="trans")s.push_back(Instruction::make(ins_t::trans,{pargs[0],pargs[1]}));
+			else if(word1=="jump")s.push_back(Instruction::make(ins_t::jump,{pargs[0]}));
+			else if(word1=="bjump")s.push_back(Instruction::make(ins_t::bjump,{pargs[0],pargs[1]}));
+			else if(word1=="die")s.push_back(Instruction::make(ins_t::die,{}));
+			else if(word1=="move")s.push_back(Instruction::make(ins_t::move,{}));
+			else if(word1=="turn")s.push_back(Instruction::make(ins_t::turn,{pargs[0]}));
+			else if(word1=="scan")s.push_back(Instruction::make(ins_t::scan,{pargs[0]}));
+			else if(word1=="create")s.push_back(Instruction::make(ins_t::create,{pargs[0],pargs[1],pargs[2]}));
+			else assert(false);
+		}
+	}
+
+	int bank=0;
+	for(Script &script : team.banks){
+		int pos=0;
+		for(Instruction &ins : script){
+			for(Argument &arg : ins.args){
+				if(arg.type==arg_t::undeflabel){
+					assert(labels.find(arg.name)!=labels.end());
+					assert(labels[arg.name].bank==bank);
+					arg.type=arg_t::number;
+					arg.num=labels[arg.name].pos-pos;
+				}
+			}
+			pos++;
+		}
+		bank++;
+	}
+
+	return team;
+}
+
+string preprocess(istream &file){
+	unordered_map<string,string> defines;
+
+	string result;
+
+	string line;
+	while(getline(file,line)){
+		if(line.find(';')!=string::npos){
+			line.erase(line.find(';'));
+		}
+		trim(line);
+		if(line.size()==0)continue;
+		squashSpaces(line);
+		lowercase(line);
+
+		string word1=line.substr(0,line.find(' '));
+		if(word1=="define"){
+			string word2r=line.find(' ')==string::npos?"":line.substr(line.find(' ')+1);
+			string word2=word2r.substr(0,word2r.find(' '));
+			string word3r=word2r.find(' ')==string::npos?"":word2r.substr(word2r.find(' ')+1);
+			assert(defines.find(word2.substr(1))==defines.end());
+			assert(word3r[0]=='{');
+			string value=word3r.substr(1);
+			assert(word3r.find('}')==string::npos||word3r.find('}')==word3r.size()-1);
+			if(word3r.back()!='}'){
+				while(true){
+					char c=file.get();
+					if(c=='}')break;
+					value+=c;
+				}
+				assert(file.get()=='\n');
+			} else {
+				value.erase(value.size()-1);
+			}
+			defines[word2.substr(1)]=value;
+		} else {
+			while(line.find('&')!=string::npos){
+				size_t start=line.find('&')+1;
+				size_t end=line.find_first_not_of("abcdefghijklmnopqrstuvwxyz0123456789._",start);
+				if(end==string::npos)end=line.size();
+				assert(defines.find(line.substr(start,end-start))!=defines.end());
+				line=line.substr(0,start-1)+defines.find(line.substr(start,end-start))->second+line.substr(end);
+			}
+			result+=line+'\n';
+		}
+	}
+
+	return result;
+}
\ No newline at end of file
diff --git a/parse.h b/parse.h
new file mode 100644
index 0000000..7af8b2a
--- /dev/null
+++ b/parse.h
@@ -0,0 +1,11 @@
+#pragma once
+
+#include <string>
+
+#include "world.h"
+
+using namespace std;
+
+
+Team assemble(const string &source);
+string preprocess(istream &file);
\ No newline at end of file
diff --git a/world.cpp b/world.cpp
index b38979a..bc08f9d 100644
--- a/world.cpp
+++ b/world.cpp
@@ -1,6 +1,7 @@
 #include <cstdlib>
 #include <cassert>
 #include <cstring>
+
 #include "world.h"
 
 using namespace std;
diff --git a/world.h b/world.h
index 2532ef5..9d89c98 100644
--- a/world.h
+++ b/world.h
@@ -2,10 +2,9 @@
 
 #include <iostream>
 #include <string>
-#include <cstring>
 #include <array>
 #include <vector>
-#include <cstdint>
+
 #include "params.h"
 #include "screenbuffer.h"