_analyze是Elasticsearch一个非常有用的API，它可以帮助你分析每一个field或者某个analyzer/tokenizer是如何分析和索引一段文字。
image.pngimage.png
返回结果字段含义：
token是一个实际被存储在索引中的词
position指明词在原文本中是第几个出现的
start_offset和end_offset表示词在原文本中占据的位置。

1、默认analyzer


GET /_analyze?
{“analyzer” : “standard”, “text” : “床前明月光”}

  1. {
  2.     "tokens": [
  3.         {
  4.             "token": "床",
  5.             "start_offset": 0,
  6.             "end_offset": 1,
  7.             "type": "<IDEOGRAPHIC>",
  8.             "position": 0
  9.         },
  10.         {
  11.             "token": "前",
  12.             "start_offset": 1,
  13.             "end_offset": 2,
  14.             "type": "<IDEOGRAPHIC>",
  15.             "position": 1
  16.         },
  17.         {
  18.             "token": "明",
  19.             "start_offset": 2,
  20.             "end_offset": 3,
  21.             "type": "<IDEOGRAPHIC>",
  22.             "position": 2
  23.         },
  24.         {
  25.             "token": "月",
  26.             "start_offset": 3,
  27.             "end_offset": 4,
  28.             "type": "<IDEOGRAPHIC>",
  29.             "position": 3
  30.         },
  31.         {
  32.             "token": "光",
  33.             "start_offset": 4,
  34.             "end_offset": 5,
  35.             "type": "<IDEOGRAPHIC>",
  36.             "position": 4
  37.         }
  38.     ]
  39. }

2、whitspace


GET /_analyze?
{“analyzer” : “whitespace”, “text” : “床前明月光”}

  1. {
  2.     "tokens": [
  3.         {
  4.             "token": "床前",
  5.             "start_offset": 0,
  6.             "end_offset": 2,
  7.             "type": "word",
  8.             "position": 0
  9.         },
  10.         {
  11.             "token": "明月光",
  12.             "start_offset": 3,
  13.             "end_offset": 6,
  14.             "type": "word",
  15.             "position": 1
  16.         }
  17.     ]
  18. }

3、使用ik分析器

GET /_analyze?
{“analyzer” : “ik_max_word”, “text” : “床前明月光”}

  1. {
  2.     "tokens": [
  3.         {
  4.             "token": "床前明月光",
  5.             "start_offset": 0,
  6.             "end_offset": 5,
  7.             "type": "CN_WORD",
  8.             "position": 0
  9.         },
  10.         {
  11.             "token": "床前",
  12.             "start_offset": 0,
  13.             "end_offset": 2,
  14.             "type": "CN_WORD",
  15.             "position": 1
  16.         },
  17.         {
  18.             "token": "明月光",
  19.             "start_offset": 2,
  20.             "end_offset": 5,
  21.             "type": "CN_WORD",
  22.             "position": 2
  23.         },
  24.         {
  25.             "token": "明月",
  26.             "start_offset": 2,
  27.             "end_offset": 4,
  28.             "type": "CN_WORD",
  29.             "position": 3
  30.         },
  31.         {
  32.             "token": "明",
  33.             "start_offset": 2,
  34.             "end_offset": 3,
  35.             "type": "CN_WORD",
  36.             "position": 4
  37.         },
  38.         {
  39.             "token": "月光",
  40.             "start_offset": 3,
  41.             "end_offset": 5,
  42.             "type": "CN_WORD",
  43.             "position": 5
  44.         },
  45.         {
  46.             "token": "月",
  47.             "start_offset": 3,
  48.             "end_offset": 4,
  49.             "type": "CN_WORD",
  50.             "position": 6
  51.         },
  52.         {
  53.             "token": "光",
  54.             "start_offset": 4,
  55.             "end_offset": 5,
  56.             "type": "CN_CHAR",
  57.             "position": 7
  58.         }
  59.     ]
  60. }


4、使用拼音分析器


GET /_analyze?
{“analyzer” : “pinyin”, “text” : “床前明月光”}

  1. {
  2.     "tokens": [
  3.         {
  4.             "token": "chuang",
  5.             "start_offset": 0,
  6.             "end_offset": 1,
  7.             "type": "word",
  8.             "position": 0
  9.         },
  10.         {
  11.             "token": "cqmyg",
  12.             "start_offset": 0,
  13.             "end_offset": 5,
  14.             "type": "word",
  15.             "position": 0
  16.         },
  17.         {
  18.             "token": "qian",
  19.             "start_offset": 1,
  20.             "end_offset": 2,
  21.             "type": "word",
  22.             "position": 1
  23.         },
  24.         {
  25.             "token": "ming",
  26.             "start_offset": 2,
  27.             "end_offset": 3,
  28.             "type": "word",
  29.             "position": 2
  30.         },
  31.         {
  32.             "token": "yue",
  33.             "start_offset": 3,
  34.             "end_offset": 4,
  35.             "type": "word",
  36.             "position": 3
  37.         },
  38.         {
  39.             "token": "guang",
  40.             "start_offset": 4,
  41.             "end_offset": 5,
  42.             "type": "word",
  43.             "position": 4
  44.         }
  45.     ]
  46. }

cfd4346a-2386-46f9-83de-0e36e366de01.jpg