最近碰到一个fgetcsv处理带中文的csv(由excel生成)的场景出现问题。表现为截取长度不对, 有两个纯中文字段没有被拆分, 貌似是fgetcsv不认中文的缘故,看了http://blog.163.com/ybbqg@126/blog/static/12236641620115143124763/ 这篇文章发现方法二可行
现将方法二的代码贴出来,作为备忘
function fgetcsv_reg(& $handle, $length = null, $d = ',', $e = '"') { $d = preg_quote($d); $e = preg_quote($e); $_line = ""; $eof=false; while ($eof != true) { $_line .= (empty ($length) ? fgets($handle) : fgets($handle, $length)); $itemcnt = preg_match_all('/' . $e . '/', $_line, $dummy); if ($itemcnt % 2 == 0) $eof = true; } $_csv_line = preg_replace('/(?: |[ ])?$/', $d, trim($_line)); $_csv_pattern = '/(' . $e . '[^' . $e . ']*(?:' . $e . $e . '[^' . $e . ']*)*' . $e . '|[^' . $d . ']*)' . $d . '/'; preg_match_all($_csv_pattern, $_csv_line, $_csv_matches); $_csv_data = $_csv_matches[1]; for ($_csv_i = 0; $_csv_i < count($_csv_data); $_csv_i++) { $_csv_data[$_csv_i] = preg_replace('/^' . $e . '(.*)' . $e . '$/s', '$1', $_csv_data[$_csv_i]); $_csv_data[$_csv_i] = str_replace($e . $e, $e, $_csv_data[$_csv_i]); } return empty ($_line) ? false : $_csv_data; }