Phrase TMS API
    1. Phrase
    2. Phrase TMS
    3. Phrase TMS API

    分析聚合 (TMS)

    文本由 Phrase Language AI 从英语机器翻译而得。

    运行聚合查询的数据存储构建在 Elasticsearch（当前版本 1.7.X）之上。Elasticsearch 提供实时搜索和聚合功能，分析 API 在其之上形成了一个精简的、增强安全性的层。示例中使用了 Elasticsearch 查询和聚合语言。

    索引

    不同类型的数据存在于不同的索引中。例如，工作 数据存在于 jobPart 索引中，而 成本 数据存在于 costs 索引中。可以通过在聚合 API 端点 URL 中指定索引来指定所需数据。

    父子文档

    有关工作的部分信息存储在 Elasticsearch 数据库中的两个不同文档中。这些文档处于 父-子 关系中。例如，有关工作项目的信息存储在父文档中，而有关工作本身的信息存储在子文档中。根据所需信息，聚合要么在数据父子聚合之前，要么在它之后，但数据聚合本身应存在于所有查询中。

    索引数据模型

    通用数据

    分析

    {
  "id": string,
  "createdBy": <User>,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "innerId": number,
  "name": string,
  "tags": string[],
  "trashed": boolean,
  "trashedBy": <User>,
  "type": string
}

    分配

    {
  "name": string,
  "linguist": <User>,
  "vendor": <Vendor>
}

    提交页面

    {
  "id": string,
  "createdBy": <User>,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "name": string,
  "tags": string[],
  "trashed": boolean,
  "urlId": string
}

    买方

    {
  "id": string,
  "name": string
}

    客户

    {
  "id": string,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "externalId": string,
  "name": string,
  "tags": string[],
  "trashed": boolean,
}

    CostCenter

    {
  "id": string,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "name": string,
  "tags": string[],
  "trashed": boolean,
}

    领域

    {
  "id": string,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "name": string,
  "tags": string[],
  "trashed": boolean
}

    工作

    {
  "id": string,
  "createdBy": <User>,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "extension": string,
  "fileName": string,
  "groupCount": number,
  "innerId": "1",
  "languagePair": string,
  "lastModified": Date,
  "localePair": string,
  "sourceLanguage": string,
  "sourceLocale": string,
  "tags": string[],
  "targetLanguage": string,
  "targetLocale": string",
  "taskId": string,
  "trashed": boolean,
  "trashedBy": <User>,
  "uid": string
}

    JobPart

    {
  "id": "19",
  "assignedTo": <Assignment>,
  "beginIndex": number,
  "buyer": <Buyer>,
  "createdBy": <User>,
  "dateCreated": Date,
  "dateDue": Date,
  "endIndex": number,
  "groupCount": number,
  "innerId": string,
  "lastModified": Date,
  "level": number,
  "status": string,
  "tags": [],
  "uid": string,
  "workflowStep": <WorkflowStep>
}

    MtEngine

    {
  "id": string,
  "deleted": boolean,
  "default_: boolean,
  "includeTags": boolean,
  "name": string,
  "tags": string[],
  "type": string,
}

    NetRateScheme

    {
  "id": string,
  "createdBy": <User>,
  "dateCreated": Date,
  "dateDeleted": Date,
  "default_": boolean,
  "deleted": boolean,
  "externalId": string,
  "name": string,
  "tags": string[],
}

    PriceList

    {
  "id": string,
  "createdBy": <User>,
  "currency": string,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "default_": boolean,
  "deleted": boolean,
  "name": string,
  "tags": string[],
  "trashed": boolean,
  "unit": string
}

    项目

    {
  "id": string,
  "buyer": <Buyer>,
  "client": <Client>,
  "costCenter": <CostCenter>,
  "createdBy": <User>,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateDue": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "domain": <Domain>,
  "innerId": number,
  "languagePairs": string[],
  "localePairs": string[],
  "mtEngine": <MtEngine>,
  "name": string,
  "note": string,
  "owner": <User>,
  "sourceLanguage": string,
  "sourceLocale": string,
  "status": string,
  "subDomain": <SubDomain>,
  "tags": string[],
  "targetLanguages": string[],
  "targetLocales": string[],
  "trashed": boolean,
  "trashedBy": <User>,
  "uid": string,
  "vendor": <Vendor>
}

    报价

    {
  "id": string,
  "createdBy: <User>,
  "currency": string,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "innerId": string,
  "name": string,
  "status": string,
  "tags": string[],
  "trashed": boolean,
  "trashedBy": <User>,
  "unit": string
}

    服务

    {
  "id": string,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "name": string,
  "publicName": string,
  "tags": string[],
  "trashed": boolean,
  "type": string
}

    SubDomain

    {
  "id": string,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "name": string,
  "tags": string[],
  "trashed": boolean
}

    用户

    {
  "id": number,
  "active": boolean,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "email": string,
  "firstName": string,
  "fullName": string,
  "innerId": number,
  "jobTitle": string,
  "lastName": string,
  "locale": string,
  "note": string,
  "role": string,
  "tags": string[],
  "timeZone": string,
  "trashed": boolean,
  "userName": string
}

    供应商

    {
  "id": string,
  "candidate": boolean,
  "dateCreated": Date,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "deleted": boolean,
  "tags": string[],
  "token": string,
  "trashed": boolean
}

    WorkflowStep

    {
  "id": string,
  "abbreviation": string,
  "dateDeleted": Date,
  "dateTrashed": Date,
  "name": string,
  "order": number,
  "tags": string[],
  "trashed": boolean
}

    分析索引

    数据聚合

    "data": {
  "children": {
    "type": "analysisType"
  }
}

    父文档

    {
  "automationWidget": <AutomationWidget>,
  "project": <Project>,
  "service": <Service>
}

    子文档

    {
  "analysis": <Analysis>,
  "jobPart": <JobPart>,
  "job": <Job>,
  "netRateScheme": <NetRateScheme>,

  "priority": number,
  "data": {
    "mt": {
      "match0": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match100": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match50": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match75": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match85": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match95": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      }
    },
    "repetitions": {
      "characters": number,
      "pages": number,
      "percent": number,
      "segments": number,
      "words": number
    },
    "tm": {
      "match0": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match100": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match101": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match50": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match75": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match85": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      },
      "match95": {
        "characters": number,
        "pages": number,
        "percent": number,
        "segments": number,
        "words": number
      }
    },
    "total": {
      "characters": number,
      "pages": number,
      "percent": number,
      "segments": number,
      "words": number
    }
  }
}

    API 索引

    数据聚合

    "data": {
  "children": {
    "type": "apiType"
  }
}

    父文档

    {
  "user": <User>
}

    子文档

    {
  "request": {
    "date": Date,
    "host": string,
    "ipv4": string,
    "ipv6": string,
    "location": string,
    "method": string
  },
  "response": {
    "date": Date,
    "duration": number,
    "status": number
  },
  "api": {
    "action": string,
    "asynch": boolean,
    "type": string,
    "uri": string,
    "ver": string
  }
}

    成本索引

    数据聚合

    "data": {
  "children": {
    "type": "costsType"
  }
}

    父文档

    {
  "automationWidget": <AutomationWidget>,
  "project": <Project>,
  "service": <Service>
}

    子文档

    {
  "analysis": <Analysis>,
  "job": <Job>,
  "jobPart": <JobPart>,
  "netRateScheme": <NetRateScheme>,
  "priceList": <PriceList>,
  "quote": <Quote>,
  "workflowStep": <WorkflowStep>,
  
  "priority": number,
  "data": {
    "mt": {
      "match0": number,
      "match100": number,
      "match50": number,
      "match75": number,
      "match85": number,
      "match95": number
    },
    "repetitions": number,
    "tm": {
      "match0": number,
      "match100": number,
      "match101": number,
      "match50": number,
      "match75": number,
      "match85": number,
      "match95": number
    },
    "total": number
  }
}

    jobPart Index

    数据聚合

    "data": {
  "children": {
    "type": "jobPartType"
  }
}

    父文档

    {
  "automationWidget": <AutomationWidget>,
  "project": <Project>,
  "service": <Service>
}

    子文档

    {
  "job": <Job>,
  "jobPart": <JobPart>

  "data": {
    "counts": {
      "chars": {
      "total": number,
      "confirmed": number,
      "notConfirmed": number,
      "locked": number,
      "notLocked": number,
      "confirmedAndLocked": number,
      "notConfirmedAndLocked": number,
      "completed": number,
      "notCompleted": number
    },
    "groups": {
      "total": number
    },
    "segments": {
      "total": number,
      "confirmed": number,
      "notConfirmed": number,
      "locked": number,
      "notLocked": number,
      "confirmedAndLocked": number,
      "notConfirmedAndLocked": number,
      "completed": number,
      "notCompleted": number,
      "mt": {
        "postEdited": number,
        "relevant": number,
        "notRelevant": number
      },
      "qa": {
        "checked": number,
        "notChecked": number
      }
    },
    "words": {
      "total": number,
      "confirmed": number,
      "notConfirmed": number,
      "locked": number,
      "notLocked": number,
      "confirmedAndLocked": number,
      "notConfirmedAndLocked": number,
      "completed": number,
      "notCompleted": number
    },
    "qa": {
      "warnings": 数字,
      "ignoredWarnings": number,
      "notIgnoredWarnings": number
    }
  }
}

    示例

    • HTTP请求在Postman中运行。

    • 通过项目经理或管理员个人资料登录，并使用登录API获取登录令牌。

    • POST requests to api/v3/analytics/jobPart?token=&lt;your_login_token&gt;

    工作总数

    查询

    {
  "aggregations": {
    "data": {
      "children": {
        "type": "jobPartType"
      }
    }
  }
}

    响应

    {
  "hits": {
    "total": 359
  },
  "aggregations": {
    "data": {
      "doc_count": 14417
    }
  }
}

    在 aggregations 字段下，data 聚合响应了 14,417 个匹配文档，显示在 doc_count 字段中。

    原文总字数

    查询

    {
  "aggregations": {
    "data": {
      "children": {
        "type": "jobPartType"
      },
      "aggs": {
        "wordCount": {
          "sum": {
            "field": "data.volume.words"
          }
        }
      }
    }
  }
}

    响应

    {
  "hits": {
    "total": 359
  },
  "aggregations": {
    "data": {
      "doc_count": 14417,
      "wordCount": {
        "value": 6893067
      }
    }
  }
}

    按译文语言划分的原文总字数

    查询

    {
  "aggregations": {
    "data": {
      "children": {
        "type": "jobPartType"
      },
      "aggs": {
        "byTargetLanguage": {
          "terms": {
            "field": "job.targetLanguage",
            "size": 3
          },
          "aggs": {
            "wordCount": {
              "sum": {
                "field": "data.volume.words"
              }
            }
          }
        }
      }
    }
  }
}

    响应

    {
  "hits": {
    "total": 359
  },
  "aggregations": {
    "data": {
      "byTargetLanguage": {
        "doc_count_error_upper_bound": 0,
        "sum_other_doc_count": 10071,
        "buckets": [
          {
            "doc_count": 1835,
            "wordCount": {
              "value": 702721
            },
            "key": "cs"
          },
          {
            "doc_count": 1491,
            "wordCount": {
              "value": 2602529
            },
            "key": "de"
          },
          {
            "doc_count": 1020,
            "wordCount": {
              "value": 92676
            },
            "key": "fi"
          }
        ]
      },
      "doc_count": 14417
    }
  }
}

    buckets 实体显示在响应中。当分析模块被要求按某个类别拆分数据时，结果表示为一个存储桶列表。每个存储桶都包含一个键，用于定义该存储桶代表的数据（在本例中为译文语言）以及一个仅针对该部分数据集特定的值（其他聚合）。

    按项目状态划分的作业总数

    查询

    {
  "aggregations": {
    "projectStatus": {
      "terms": {
        "field": "project.status"
      },
      "aggs": {
        "data": {
          "children": {
            "type": "jobPartType"
          }
        }
      }
    }
  }
}

    响应

    {
  "hits": {
    "total": 359
  },
  "aggregations": {
    "projectStatus": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "doc_count": 326,
          "data": {
            "doc_count": 14318
          },
          "key": "NEW"
        },
        {
          "doc_count": 31,
          "data": {
            "doc_count": 89
          },
          "key": "COMPLETED"
        },
        {
          "doc_count": 1,
          "data": {
            "doc_count": 4
          },
          "key": "ASSIGNED"
        },
        {
          "doc_count": 1,
          "data": {
            "doc_count": 6
          },
          "key": "DECLINED_BY_VENDOR"
        }
      ]
    }
  }
}

    分析模块已被告知在 数据 聚合之前按项目状态拆分数据。

    来自新项目的作业总数

    查询

    {
  "filter": {
    "term": {
      "project.status": "NEW"
    }
  },
  "aggregations": {
    "data": {
      "children": {
        "type": "jobPartType"
      }
    }
  }
}

    响应

    {
  "hits": {
    "total": 326
  },
  "aggregations": {
    "data": {
      "doc_count": 14318
    }
  }
}

    筛选 字段用于查询中。这会在后续聚合之前缩小数据范围。

    这篇文章有帮助吗？
    ★ ★ ★ ★ ★

    Sorry about that! In what way was it not helpful?

    The article didn’t address my problem.
    I couldn’t understand the article.
    The feature doesn’t do what I need.
    Other reason.

    Note that feedback is provided anonymously so we aren't able to reply to questions.
    If you'd like to ask a question, submit a request to our Support team.
    Thank you for your feedback.