PHP智能识别收货地址信息实例

功能需求：用户输入混合的收货地址，能智能识别出地址，手机，姓名

准备:需要两张表，一张地区表和一张姓氏表 (地区表得到应该不难，姓氏表我是搜索中国姓氏自制的哈，底部会附上表结构)

思路：主要思路分两种，一种是用户正常输入全地址，则顺序按地区等级匹配地址；另一种用户非正常输入（省市区有缺少的），则全面模糊搜索表，再根据结果对比原地址。

提醒：手机可以根据自己需求修改正则；

名字只匹配中文，可以根据自己的需求修改姓氏表以及正则

地址匹配暂无发现问题

效果图：

代码：

<?php
class distinguishaddress {
/**
 * 类的入口方法
 * 传入地址信息自动识别，并返回最高匹配结果
 * 如果地址新增，则需要删除缓存文件重新缓存
 * @param $address
 **/
function getaddressresult($address){
 // 优先第一种方法
 $result = $this->getaddressarrar($address);
 // 如果结果不理想，再模糊去匹配
 if($result['level'] != 3){
  $result_sub = $this->addressvague($address);
  // 只有全匹配对才替换，否则不做任何改变
  if($result_sub['level'] == 3){
   $result = $result_sub;
  }
 }
 // 联系方式-优先匹配电话
 if(preg_match('/1\d{10}/', $address, $mobiles)){ // 手机
  $result['mobile'] = $mobiles[0];
 } else if(preg_match('/(\d{3,4}-)?\d{7,8}/', $address, $mobiles)){ // 固定电话
  $result['mobile'] = $mobiles[0];
 }
 // 识别姓名-必须空格分享的--概率
 preg_match_all('/[\x{4e00}-\x{9fa5}]{2,}/iu', $address,$names);
 if($names){
  $name_where = '';
  foreach ($names[0] as $name){
   // 必须是大于1个字符且小于5个字符的
   if(1 < mb_strlen($name,'utf-8') && mb_strlen($name, 'utf-8') < 5){
    $sub_name = mb_substr($name, 0, 1, 'utf-8');
    $name_where .= "name like '{$sub_name}%' or ";
   }
  }
  if(!empty($name_where)){
   $name_where = substr($name_where, 0, -3);
   $names_sql = "select name from surname where {$name_where} order by sort desc";
   $list = db::getinstance('dbtrade')->getall($names_sql);
   // 统计有多少种可能性-姓名
   $result['name_num'] = count($list);
   if($list) {
    $name_first = $list[0]['name'];
    foreach ($names[0] as $name){
     $len = mb_strlen($name_first, 'utf-8');
     if (mb_substr($name, 0, $len, 'utf-8') == $name_first){
      $result['name'] = $name;
     }
    }
   }
  }
 }
 // 去掉详细里面的姓名和电话
 $result['info'] = str_replace($result['mobile'], '', $result['info']);
 $result['info'] = str_replace($result['name'], '', $result['info']);
 $result['info'] = $result['province']['region_name'] . $result['city']['region_name'] . $result['district']['region_name'] . $result['info'];
 return $this->getcitylevellist($result);
}
/**
 * 获取对应城市等级列表
 **/
function getcitylevellist($result){
 // 获取所有地址递归列表
 $regions = $this->getregiontreelist();
 // 获取省份列表- 只有存在值才返回对应列表
 $province_id = $result['province']['region_id'];
 if ($province_id) {
  foreach ($regions as $region){
   unset($region['childs']);
   $result['province_list'][] = $region;
  }
 }
 // 获取城市列表- 只有存在值才返回对应列表
 $city_id = $result['city']['region_id'];
 if ($city_id) {
  foreach ($regions[$province_id]['childs'] as $region){
   unset($region['childs']);
   $result['city_list'][] = $region;
  }
 }
 // 获取地区列表- 只有存在值才返回对应列表
 $district_id = $result['district']['region_id'];
 if ($district_id) {
  foreach ($regions[$province_id]['childs'][$city_id]['childs'] as $region){
   unset($region['childs']);
   $result['district_list'][] = $region;
  }
 }
 return $result;
}
/**
 * 获取所有地址递归列表
 **/
function getregiontreelist(){
 // io
 $file_name = 'regions.json';
 if(is_file($file_name)){
  $regions = file_get_contents($file_name);
  $regions = json_decode($regions, true);
 } else {
  $region_sql = "select region_id,region_name,parent_id from region";
  $regions = db::getinstance('dbtrade')->getall($region_sql);
  $regions = $this->arraykey($regions);
  file_put_contents($file_name, json_encode($regions));
 }
 return $regions;
}
/**
 * 第一种方法
 * 根据地址列表递归查找准确地址
 * @param $address
 * @return array
 **/
function getaddressarrar($address){
 // 获取所有地址递归列表
 $regions = $this->getregiontreelist();
 // 初始化数据
 $province = $city = $district = array();
 // 先查找省份-第一级地区
 $province = $this->checkaddress($address, $regions);
 if($province){
  // 查找城市-第二级地区
  $city = $this->checkaddress($address, $province['list']);
  if($city){
   // 查找地区-第三级地区
   // *自治区那曲市色尼区辽宁南路*公路 第三个参数因为这个地址冲突取消强制
   $district = $this->checkaddress($address, $city['list']);
  }
 }
 return $this->getaddressinfo($address, $province, $city, $district);
}
 /**
  * 第二种方法
  * 地址模糊查找
  **/
function addressvague($address){
 $res = preg_match_all('/\s{2}[自市区镇县乡岛州]/iu', $address,$arr);
 if(!$res) return false;
 $where = ' where ';
 foreach ($arr[0] as $value){
  if(strpos($value, '小区') === false && strpos($value, '开发区') === false){
   $where .= "region_name like '%{$value}' or ";
  }
 }
 $where = substr($where,0,-3);
 $region_sql = "select region_id,region_name,parent_id,region_type from region " . $where;
 $citys = $globals['db']->getall($region_sql);
 // 匹配所有地址
 $result = array();
 foreach ($citys as &$city){
  // 所有相关联的地区id
  $city_ids = array();
  if($city['region_type'] == 2) {
   $city_ids = array($city['parent_id'], $city['region_id']);
   // 尝试能不能匹配第三级
   $region_sql = "select region_id,region_name,parent_id,region_type,left(region_name,2) as ab_name from region where parent_id='{$city['region_id']}'" ;
   $areas = $globals['db']->getall($region_sql);
   foreach ($areas as $row){
    if(mb_strpos($address,$row['ab_name'])){
     $city_ids[] = $row['region_id'];
    }
   }
  } else if($city['region_type'] == 3){
   $region_sql = "select parent_id from region where region_id='{$city['parent_id']}'" ;
   $city['province_id'] = $globals['db']->getone($region_sql);
   $city_ids = array($city['parent_id'], $city['region_id'], $city['province_id']);
  }
  // 查找该单词所有相关的地区记录
  $where = " where region_id in(" . join(',', $city_ids) . ")";
  $region_sql = "select region_id,region_name,parent_id,region_type,left(region_name,2) as ab_name from region " . $where . ' order by region_id asc';
  $city_list = $globals['db']->getall($region_sql);
  sort($city_ids);
  $key = array_pop($city_ids);
  $result[$key] = $city_list;
  sort($result);
 }
 if($result){
  list($province, $city, $area) = $result[0];
  return $this->getaddressinfo($address, $province, $city, $area);
 }
 return false;
}
/**
 * 匹配正确的城市地址
 * @param $address
 * @param $city_list
 * @param int $force
 * @param int $str_len
 * @return array
 **/
function checkaddress($address, $city_list, $force=false, $str_len=2){
 $num = 0;
 $list = array();
 $result = array();
 // 遍历所有可能存在的城市
 foreach ($city_list as $city_key=>$city){
  $city_name = mb_substr($city['region_name'], 0, $str_len,'utf-8');
  // 判断是否存包含当前地址字符
  $city_arr = explode($city_name, $address);
  // 如果存在相关字眼，保存该地址的所有子地址
  if(count($city_arr) >= 2){
   // 必须名称长度同时达到当前比对长度
   if(strlen($city['region_name']) < $str_len){
    continue;
   }
   $num ++;
   $list = $list + $city['childs'];

   $result[] = array(
    'region_id' => $city['region_id'],
    'region_name' => $city['region_name'],
    'list' =>$list,
   );
  }
 }
 // 如果有多个存在，则加大字符匹配长度
 if($num > 1 || $force){
  $region_name1 = $result[0]['region_name'];
  $region_name2 = $result[1]['region_name'];

  if(strlen($region_name1) == strlen($region_name2) && strlen($region_name1) == $str_len){
   $region_id1 = $result[0]['region_id'];
   $region_id2 = $result[1]['region_id'];
   $index = $region_id1 > $region_id2 ? 1 : 0;
   $result = $result[$index];
   return $result;
  }
  return $this->checkaddress($address, $city_list, $force, $str_len+1);
 } else {
  $result[0]['list'] = $list;
  return $result[0];
 }
}
/**
 * 根据原地址返回详细信息
 * @param $address
 * @param $province
 * @param $city
 * @param $area
 * @return array
 **/
function getaddressinfo($address, $province, $city, $district){
 // 查找最后出现的地址 - 截取详细信息
 $find_str = '';
 if($province['region_name']){
  $find_str = $province['region_name'];
  if($city['region_name']){
   $find_str = $city['region_name'];
   if($district['region_name']){
    $find_str = $district['region_name'];
   }
  }
 }
 // 截取详细的信息
 $find_str_len = mb_strlen($find_str,'utf-8');
 for($i=0; $i<$find_str_len-1; $i++){
  $substr = mb_substr($find_str,0,$find_str_len - $i, 'utf-8');
  $end_index = mb_strpos($address, $substr);
  if ($end_index){
   $address = mb_substr($address, $end_index + mb_strlen($substr) , mb_strlen($address) - $end_index);
  }
 }
 !empty($find_str) && $find_str = '|\s*' . $find_str;
 $area['info'] = preg_replace("/\s*|,|，|:|：{$find_str}/i", '', $address);
 $level = 0;
 if($district['region_name']){
  $level = 3;
 } else if($city['region_name']){
  $level = 2;
 } else if ($province['region_name']) {
  $level = 1;
 }
 return array(
  'province' => array('region_id'=>$province['region_id'], 'region_name'=>$province['region_name']),
  'city'  => array('region_id'=>$city['region_id'], 'region_name'=>$city['region_name']),
  'district'  => array('region_id'=>$district['region_id'], 'region_name'=>$district['region_name']),
  'info'  => $area['info'],
  'level'  => $level,
 );
}
/**
 * 递归所有地址成无限分类数组
 * @param $data
 * @param int $region_id
 * @return array
 **/
function arraykey($data, $region_id=1){
 $result = array();
 foreach ($data as $row){
  if($region_id == $row['parent_id']){
   $key = $row['region_id'];
   $row['childs'] = $this->arraykey($data, $row['region_id']);
   $result[$key] = $row;
  }
 }
 return $result;
}
}
?>

姓氏surname表（id,姓，优先匹配顺序）

drop table if exists `surname`;
create table `surname` (
 `id` int(11) not null auto_increment,
 `name` char(10) character set utf8 collate utf8_general_ci null default null,
 `sort` int(11) null default null,
 primary key (`id`) using btree,
 index `name`(`name`) using btree,
 index `sort`(`sort`) using btree
) engine = innodb auto_increment = 481 character set = utf8 collate = utf8_general_ci comment = '姓氏表' row_format = compact;

地址region表（）

create table `region` (
 `region_id` smallint(5) unsigned not null auto_increment,
 `parent_id` smallint(5) unsigned not null default 0,
 `region_name` varchar(120) character set utf8 collate utf8_general_ci not null default '',
 `region_type` tinyint(1) not null default 2,
 `agency_id` smallint(5) unsigned not null default 0,
 primary key (`region_id`) using btree,
 index `parent_id`(`parent_id`) using btree,
 index `region_type`(`region_type`) using btree,
) engine = innodb auto_increment = 3956 avg_row_length = 44 character set = utf8 collate = utf8_general_ci row_format = compact;

总结

以上就是这篇文章的全部内容了，希望本文的内容对大家的学习或者工作具有一定的参考学习价值，谢谢大家对的支持。如果你想了解更多相关内容请查看下面相关链接