// Read a single-file C++ program having a very specific structure, and split
// it up into multiple separate compilation units to reduce the work needed to
// rebuild after a small change. Write each compilation unit only if it has
// changed from what was on disk before.
//
// This tool is tightly coupled with the build system for this project. The
// makefile already auto-generates various things; we only do here what
// standard unix tools can't easily do.
//
// Usage:
//  cleave [input C++ file] [existing output directory]
//
// The input C++ file has the following structure:
//   [#includes]
//   [type definitions]
//   // Globals
//   [global variable definitions]
//   // End Globals
//   [function definitions]
//
// Afterwards, the output directory contains:
//   header -- everything before the '// Globals' delimiter
//   global_definitions_list -- everything between '// Globals' and '// End Globals' delimiters
//   [.cc files partitioning function definitions]
//
// Each output function definition file contains:
//   #include "header"
//   #include "global_declarations_list"
//   [function definitions]
//
// To preserve the original layer-based line numbers in error messages and the
// debugger, we'll chunk the files only at boundaries where we encounter a
// '#line ' directive (generated by the previous tangle/ stage) between
// functions.
//
// One exception: the first file emitted #includes "global_definitions_list" instead
// of "global_declarations_list"

// Tune this parameter to balance time for initial vs incremental build.
//
//   decrease value -> faster initial build
//   increase value -> faster incremental build
int Num_compilation_units = 3;

#include<assert.h>
#include<cstdlib>
#include<cstring>

#include<vector>
using std::vector;
#include<list>
using std::list;
#include<utility>
using std::pair;

#include<string>
using std::string;

#include<iostream>
using std::istream;
using std::ostream;
using std::cin;
using std::cout;
using std::cerr;

#include<sstream>
using std::istringstream;
using std::ostringstream;

#include<fstream>
using std::ifstream;
using std::ofstream;

#include <locale>
using std::isspace;  // unicode-aware

string trim(const string& s) {
  string::const_iterator first = s.begin();
  while (first != s.end() && isspace(*first))
    ++first;
  if (first == s.end()) return "";

  string::const_iterator last = --s.end();
  while (last != s.begin() && isspace(*last))
    --last;
  ++last;
  return string(first, last);
}

bool starts_with(const string& s, const string& pat) {
  string::const_iterator a=s.begin(), b=pat.begin();
  for (/*nada*/; a!=s.end() && b!=pat.end(); ++a, ++b)
    if (*a != *b) return false;
  return b == pat.end();
}

bool has_data(istream& in) {
  return in && !in.eof();
}

void slurp(const string& filename, vector<string>& lines) {
  lines.clear();
  ifstream in(filename.c_str());
  while (has_data(in)) {
    string curr_line;
    getline(in, curr_line);
    lines.push_back(curr_line);
  }
}

size_t slurp_some_functions(const vector<string>& in, size_t start, vector<string>& out, bool first) {
  out.clear();
  if (start >= in.size()) return start;
  out.push_back("#include \"header\"");
  if (first)
    out.push_back("#include \"global_definitions_list\"");
  else
    out.push_back("#include \"global_declarations_list\"");
  out.push_back("");
  size_t curr = start;
  while (true) {
    if (curr >= in.size()) break;
    if (out.size() >= in.size()/Num_compilation_units) break;
    while (curr < in.size()) {
      // read functions -- lines until unindented '}'
      while (curr < in.size()) {
        const string& line = in.at(curr);
//?         cerr << curr << ": adding to function: " << line << '\n';
        out.push_back(line);  ++curr;
        if (!line.empty() && line.at(0) == '}') break;
      }
      // now look for a '#line' directive before the next non-comment non-empty
      // line
      while (curr < in.size()) {
        const string& line = in.at(curr);
        if (starts_with(line, "#line ")) goto try_return;
        out.push_back(line);   ++curr;
        if (trim(line).empty()) continue;
        if (starts_with(trim(line), "//")) cont<style>pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlig