gistfile1.txt

#include <dirent.h>

#include <stdio.h>

#include <stdlib.h>

#include <string.h>

#include "unicode/ucol.h"

int main(int argc, char * argv[]) {
  DIR * d;
  struct dirent * dir;
  d = opendir(argv[1]);
  int size = 0;

  if (d) {
    while ((dir = readdir(d)) != NULL) {
      char * name = dir -> d_name;
      if (name[0] == '.') {
        continue;
      }
      size++;
    }
    closedir(d);
  }

  d = opendir(argv[1]);
  char * files[size];
  char * files1[size];
  int idx = 0;

  if (d) {
    while ((dir = readdir(d)) != NULL) {
      char * name = dir -> d_name;
      if (name[0] == '.') {
        continue;
      }
      files[idx] = name;
      files1[idx] = name;
      idx++;
    }
  }

  closedir(d);

  for (int i = 0; i < size - 1; i++) {
    for (int j = i + 1; j < size; j++) {
      if ((strcoll(files[i], files[j])) > 0) {
        char * tmp;
        tmp = files[i];
        files[i] = files[j];
        files[j] = tmp;
      }
    }
  }

  for (int i = 0; i < size; i++) {
    printf("%s\n", files[i]);
  }

  printf("-------------------\n");

  UErrorCode status = U_ZERO_ERROR;
  UCollator * coll = ucol_open("zh_CN", & status);
  if (U_SUCCESS(status)) {
    for (int i = 0; i < size - 1; i++) {
      for (int j = i + 1; j < size; j++) {
        UChar source[256];
        UChar target[256];
        int32_t sourceCap = 256;
        int32_t pSourceLen;
        int32_t targetCap = 256;
        int32_t pTargetLen;

        UErrorCode err = U_ZERO_ERROR;
        u_strFromUTF8(source, sourceCap, & pSourceLen, files1[i], strlen(files1[i]) + 1, & err);
        u_strFromUTF8(target, targetCap, & pTargetLen, files1[j], strlen(files1[j]) + 1, & err);

        if (ucol_strcoll(coll, source, u_strlen(source), target, u_strlen(target)) == UCOL_GREATER) {
          char * tmp1;
          tmp1 = files1[i];
          files1[i] = files1[j];
          files1[j] = tmp1;
        }
      }
    }
    ucol_close(coll);
  }

  for (int i = 0; i < size; i++) {
    printf("%s\n", files1[i]);
  }

  return 0;
}

不一样的，strcoll 是 unicode codepoint 排序。libicu collator 才有比如 pinyin 这样的排序