5133 - show instruction source in trace

It's a little hacky in some corner cases. In particular, if debug information
isn't available the trace will contain duplicated lines. This is because
I don't want the core trace lines all my tests rely on (introduced in the
'vm' layer) to have to know about debug info (introduced in the 'labels'
and 'debug' layers).

Thanks Charles Saternos for the feedback and suggestion!

7 files changed, 104 insertions, 14 deletions

diff --git a/browse_trace/browse_trace.cc b/browse_trace/browse_trace.cc
index cc03f5ce..abfd6daa 100644
--- a/browse_trace/browse_trace.cc
+++ b/browse_trace/browse_trace.cc
@@ -429,16 +429,22 @@ void render() {
     if (!contains_key(Trace_index, screen_row)) break;
     trace_line& curr_line = Trace_stream->past_lines.at(get(Trace_index, screen_row));
     ostringstream out;
-    out << std::setw(4) << curr_line.depth << ' ' << curr_line.label << ": " << curr_line.contents;
     if (screen_row < tb_height()-1) {
       int delta = lines_hidden(screen_row);
       // home-brew escape sequence for red
       if (delta > 1) {
         if (delta > 999) out << static_cast<char>(1);
-        out << " (" << delta << ")";
+        out << std::setw(6) << delta << "| ";
         if (delta > 999) out << static_cast<char>(2);
       }
+      else {
+        out << "        ";
+      }
     }
+    else {
+      out << "        ";
+    }
+    out << std::setw(4) << curr_line.depth << ' ' << curr_line.label << ": " << curr_line.contents;
     render_line(screen_row, out.str(), screen_row == Display_row);
   }
   // clear rest of screen
@@ -467,8 +473,8 @@ void render_line(int screen_row, const string& s, bool cursor_line) {
     char c = s.at(col+Left_of_screen);  // todo: unicode
     if (c == '\n') c = ';';  // replace newlines with semi-colons
     // escapes. hack: can't start a line with them.
-    if (c == '\1') { color = /*red*/1;  c = ' '; }
-    if (c == '\2') { color = TB_WHITE;  c = ' '; }
+    if (c == '\1') { color = /*red*/1;  continue; }
+    if (c == '\2') { color = TB_WHITE;  continue; }
     if (in_range(highlight_ranges, col+Left_of_screen))
       tb_print(c, TB_BLACK, /*yellow*/11);
     else
diff --git a/subx/001help.cc b/subx/001help.cc
index 1b3f64dd..79589cf8 100644
--- a/subx/001help.cc
+++ b/subx/001help.cc
@@ -81,10 +81,8 @@ void init_help() {
     "- Add '--trace' to any of these commands to print a trace to stderr\n"
     "  for debugging purposes.\n"
     "- Add '--debug' to add information to traces. 'subx --debug translate' will\n"
-    "  save (to a file called 'labels') the mapping from labels to addresses that\n"
-    "  it computes during translation. This file is then available to\n"
-    "  'subx --debug --trace run' which prints out label names in the trace as it\n"
-    "  encounters them.\n"
+    "  save various mappings to files that 'subx --debug --trace run'\n"
+    "  can use to make traces more informative.\n"
     "\n"
     "Options starting with '--' must always come before any other arguments.\n"
     "\n"
diff --git a/subx/010---vm.cc b/subx/010---vm.cc
index f4fb8119..31e5608f 100644
--- a/subx/010---vm.cc
+++ b/subx/010---vm.cc
@@ -305,7 +305,7 @@ void run_one_instruction() {
   }
   uint32_t inst_start_address = EIP;
   op = next();
-  trace(Callstack_depth, "run") << "0x" << HEXWORD << inst_start_address << " opcode: " << HEXBYTE << NUM(op) << end();
+  trace(Callstack_depth+1, "run") << "0x" << HEXWORD << inst_start_address << " opcode: " << HEXBYTE << NUM(op) << end();
   switch (op) {
   case 0xf4:  // hlt
     EIP = End_of_program;
@@ -369,7 +369,7 @@ inline uint8_t next() {
 
 void dump_registers() {
   ostringstream out;
-  out << "registers: ";
+  out << "registers before: ";
   for (int i = 0;  i < NUM_INT_REGISTERS;  ++i) {
     if (i > 0) out << "; ";
     out << "  " << i << ": " << std::hex << std::setw(8) << std::setfill('_') << Reg[i].u;
diff --git a/subx/035labels.cc b/subx/035labels.cc
index f1eb6510..f3131168 100644
--- a/subx/035labels.cc
+++ b/subx/035labels.cc
@@ -138,6 +138,8 @@ void compute_byte_indices_for_labels(const segment& code, map<string, int32_t>&
   int current_byte = 0;
   for (int i = 0;  i < SIZE(code.lines);  ++i) {
     const line& inst = code.lines.at(i);
+    if (Source_lines_file.is_open() && !inst.original.empty() && /*not a label*/ *inst.words.at(0).data.rbegin() != ':')
+      Source_lines_file << "0x" << HEXWORD << (code.start + current_byte) << ' ' << inst.original << '\n';
     for (int j = 0;  j < SIZE(inst.words);  ++j) {
       const word& curr = inst.words.at(j);
       // hack: if we have any operand metadata left after previous transforms,
@@ -185,6 +187,7 @@ void compute_byte_indices_for_labels(const segment& code, map<string, int32_t>&
 :(before "End Globals")
 bool Dump_debug_info = false;  // currently used only by 'subx translate'
 ofstream Labels_file;
+ofstream Source_lines_file;
 :(before "End Commandline Options")
 else if (is_equal(*arg, "--debug")) {
   Dump_debug_info = true;
@@ -195,10 +198,14 @@ else if (is_equal(*arg, "--debug")) {
 if (Dump_debug_info) {
   cerr << "saving address->label information to 'labels'\n";
   Labels_file.open("labels");
+  cerr << "saving address->source information to 'source_lines'\n";
+  Source_lines_file.open("source_lines");
 }
 :(before "End subx translate")
-if (Dump_debug_info)
+if (Dump_debug_info) {
   Labels_file.close();
+  Source_lines_file.close();
+}
 
 :(code)
 void drop_labels(segment& code) {
diff --git a/subx/038---literal_strings.cc b/subx/038---literal_strings.cc
index a795ce23..65a7740b 100644
--- a/subx/038---literal_strings.cc
+++ b/subx/038---literal_strings.cc
@@ -104,6 +104,7 @@ void parse_instruction_character_by_character(const string& line_data, vector<li
   istringstream in(line_data);
   in >> std::noskipws;
   line result;
+  result.original = line_data;
   // add tokens (words or strings) one by one
   while (has_data(in)) {
     skip_whitespace(in);
diff --git a/subx/039debug.cc b/subx/039debug.cc
index ebf39034..26bb5f7a 100644
--- a/subx/039debug.cc
+++ b/subx/039debug.cc
@@ -6,11 +6,13 @@
 
 :(before "End Globals")
 map</*address*/uint32_t, string> Symbol_name;  // used only by 'subx run'
+map</*address*/uint32_t, string> Source_line;  // used only by 'subx run'
 :(before "End --debug Settings")
-load_map("labels");
+load_labels();
+load_source_lines();
 :(code)
-void load_map(const string& map_filename) {
-  ifstream fin(map_filename.c_str());
+void load_labels() {
+  ifstream fin("labels");
   fin >> std::hex;
   while (has_data(fin)) {
     uint32_t addr = 0;
@@ -21,9 +23,43 @@ void load_map(const string& map_filename) {
   }
 }
 
+void load_source_lines() {
+  ifstream fin("source_lines");
+  fin >> std::hex;
+  while (has_data(fin)) {
+    uint32_t addr = 0;
+    fin >> addr;
+    string line;
+    getline(fin, line);
+    put(Source_line, addr, hacky_squeeze_out_whitespace(line));
+  }
+}
+
 :(after "Run One Instruction")
 if (contains_key(Symbol_name, EIP))
   trace(Callstack_depth, "run") << "== label " << get(Symbol_name, EIP) << end();
+if (contains_key(Source_line, EIP))
+  trace(Callstack_depth, "run") << "0x" << HEXWORD << EIP << ": " << get(Source_line, EIP) << end();
+else
+  // no source line info; do what you can
+  trace(Callstack_depth, "run") << "0x" << HEXWORD << EIP << ": " << debug_info(EIP) << end();
+
+:(code)
+string debug_info(uint32_t inst_address) {
+  uint8_t op = read_mem_u8(EIP);
+  if (op != 0xe8) {
+    ostringstream out;
+    out << HEXBYTE << NUM(op);
+    return out.str();
+  }
+  int32_t offset = read_mem_i32(EIP+/*skip op*/1);
+  uint32_t next_eip = EIP+/*inst length*/5+offset;
+  if (contains_key(Symbol_name, next_eip))
+    return "e8/call "+get(Symbol_name, next_eip);
+  ostringstream out;
+  out << "e8/call 0x" << HEXWORD << next_eip;
+  return out.str();
+}
 
 //: If a label starts with '$watch-', make a note of the effective address
 //: computed by the next instruction. Start dumping out its contents to the
@@ -54,3 +90,44 @@ if (!Watch_this_effective_address.empty()) {
   dbg << "now watching " << HEXWORD << addr << " for " << Watch_this_effective_address << end();
   put(Watch_points, Watch_this_effective_address, addr);
 }
+
+//: helpers
+
+:(code)
+string hacky_squeeze_out_whitespace(const string& s) {
+  // strip whitespace at start
+  string::const_iterator first = s.begin();
+  while (first != s.end() && isspace(*first))
+    ++first;
+  if (first == s.end()) return "";
+
+  // strip whitespace at end
+  string::const_iterator last = --s.end();
+  while (last != s.begin() && isspace(*last))
+    --last;
+  ++last;
+
+  // replace runs of spaces/dots with single space until comment or string
+  // TODO:
+  //   leave alone dots not surrounded by whitespace
+  //   leave alone '#' within word
+  //   leave alone '"' within word
+  //   squeeze spaces after end of string
+  ostringstream out;
+  bool previous_was_space = false;
+  bool in_comment_or_string = false;
+  for (string::const_iterator curr = first;  curr != last;  ++curr) {
+    if (in_comment_or_string)
+      out << *curr;
+    else if (isspace(*curr) || *curr == '.')
+      previous_was_space = true;
+    else {
+      if (previous_was_space)
+        out << ' ';
+      out << *curr;
+      previous_was_space = false;
+      if (*curr == '#' || *curr == '"') in_comment_or_string = true;
+    }
+  }
+  return out.str();
+}
diff --git a/subx/Readme.md b/subx/Readme.md
index 15cb9972..e8e4ad6d 100644
--- a/subx/Readme.md
+++ b/subx/Readme.md
@@ -43,6 +43,7 @@ Emulated runs generate a trace that permits [time-travel debugging](https://gith
   ```sh
   $ ./subx --debug translate examples/factorial.subx -o examples/factorial
   saving address->label information to 'labels'
+  saving address->source information to 'source_lines'
   $ ./subx --debug --trace run examples/factorial
   saving trace to 'last_run'
   $ ../browse_trace/browse_trace last_run  # text-mode debugger UI