docs.sheetjs.com/docz/static/stata/cleanfile.c

#include "stplugin.h"
#include "duktape.h"

#define DOIT(cmd) duk_eval_string_noresult(ctx, cmd);

#define FAIL_DUK(cmd) { \
  const char *errmsg = duk_safe_to_string(ctx, -1); \
  duk_destroy_heap(ctx); \
  snprintf(failbuf, 255, "error in %s: %s", cmd, errmsg); \
  SF_error(failbuf); \
  return NULL; \
}

#define FAIL_LOAD { \
  duk_push_undefined(ctx); \
  SF_error("Error in load_file"); \
  return 1; \
}

static char *read_file(const char *filename, size_t *sz) {
  FILE *f = fopen(filename, "rb");
  if(!f) return NULL;
  long fsize; { fseek(f, 0, SEEK_END); fsize = ftell(f); fseek(f, 0, SEEK_SET); }
  char *buf = (char *)malloc(fsize * sizeof(char));
  *sz = fread((void *) buf, 1, fsize, f);
  fclose(f);
  return buf;
}

static duk_int_t eval_file(duk_context *ctx, const char *filename) {
  size_t len; char *buf = read_file(filename, &len);
  if(!buf) FAIL_LOAD

  duk_push_lstring(ctx, (const char *)buf, (duk_size_t)len);
  duk_int_t retval = duk_peval(ctx);
  duk_pop(ctx);
  return retval;
}

static duk_int_t load_file(duk_context *ctx, const char *filename, const char *var) {
  size_t len; char *buf = read_file(filename, &len);
  if(!buf) FAIL_LOAD

  duk_push_external_buffer(ctx);
  duk_config_buffer(ctx, -1, buf, len);
  duk_put_global_string(ctx, var);
  return 0;
}

static duk_int_t save_file(duk_context *ctx, const char *filename, const char *var) {
  duk_get_global_string(ctx, var);
  duk_size_t sz;
  char *buf = (char *)duk_get_buffer_data(ctx, -1, &sz);

  if(!buf) return 1;
  FILE *f = fopen(filename, "wb"); fwrite(buf, 1, sz, f); fclose(f);
  return 0;
}

STDLL stata_call(int argc, char *argv[])
{
  duk_int_t res = 0;
  char failbuf[255];

  /* initialize duktape */
  duk_context *ctx = duk_create_heap_default();
  /* duktape does not expose a standard "global" by default */
  DOIT("var global = (function(){ return this; }).call(null);")

  /* load SheetJS library */
  res = eval_file(ctx, "shim.min.js");
  if(res != 0) FAIL_DUK("shim load")
  res = eval_file(ctx, "xlsx.full.min.js");
  if(res != 0) FAIL_DUK("library load")

  /* print SheetJS version number */
  //duk_eval_string(ctx, "XLSX.version");
  //char verbuf[255];
  //snprintf(verbuf, 255, "SheetJS library version: %s\n", duk_get_string(ctx, -1));
  //SF_display(verbuf);

  /* read file */
  res = load_file(ctx, argv[0], "buf");
  if(res != 0) FAIL_DUK("file load")

  /* parse workbook */
  DOIT("wb = XLSX.read(buf.slice(0, buf.length), {type:'buffer'});");

  /* print CSV */
  duk_eval_string(ctx, "wb.SheetNames.length");
  duk_uint_t wscnt = duk_get_uint(ctx, -1);
  duk_pop(ctx);

  /* if argument 2 is "verbose", print CSV contents */
  if(argc>1 && !strncmp(argv[1], "verbose", 7)) for(uint32_t wsidx = 0; wsidx < wscnt; ++wsidx) {
    /* select n-th worksheet */
    char wsbuf[80];
    snprintf(wsbuf, 80, "ws = wb.Sheets[wsname = wb.SheetNames[%d]]", wsidx); \
    DOIT(wsbuf);

    duk_eval_string(ctx, "wsname");
    char namebuf[60];
    snprintf(namebuf, 60, "Worksheet %d Name: %s\n", wsidx, duk_get_string(ctx, -1));
    duk_pop(ctx);
    SF_display(namebuf);

    /* convert to CSV */
    duk_eval_string(ctx, "XLSX.utils.sheet_to_csv(ws)");
    const char *csv = duk_get_string(ctx, -1);

    /* print each row in a separate line */
    char *tok = strtok(csv, "\n");
    while(tok != NULL) {
      SF_display(tok);
      SF_display("\n");
      tok = strtok(NULL, "\n");
    }
    duk_pop(ctx);
  }

  /* write to sheetjs.tmp.xlsx */
  DOIT("newbuf = (XLSX.write(wb, {type:'array', bookType:'xlsx'}));");\
  res = save_file(ctx, "sheetjs.tmp.xlsx", "newbuf");\
  if(res != 0) FAIL_DUK("save sheetjsw.xlsx")

  SF_display("\n");
  SF_display("Saved to `sheetjs.tmp.xlsx`\n");
  SF_display("{stata import excel \"sheetjs.tmp.xlsx\", firstrow} will read the first sheet and use headers\n");
  SF_display("for more help, see {help import excel}\n");
  return(0) ;
}