dsh-data-cleaning-agent 0.8.14 → 0.8.15
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +4 -0
- package/README.en.md +7 -1
- package/README.md +24 -1
- package/marketing/metadata.json +23 -6
- package/package.json +18 -3
package/CHANGELOG.md
CHANGED
package/README.en.md
CHANGED
|
@@ -1,8 +1,14 @@
|
|
|
1
1
|
# dsh-data-cleaning-agent
|
|
2
2
|
|
|
3
|
+
Data cleaning and data enrichment for CSV/XLSX/JSON enterprise lists in DeepSeek Harness, including spreadsheet cleaning, deduplication, profiling, optional Qichacha MCP and exports.
|
|
4
|
+
|
|
5
|
+
Install a pinned release using the command in the [Chinese quick start](README.md), review the preview or evidence before confirming, and keep the previous version and task-directory backup for rollback. Qichacha calls use the customer's authorized account.
|
|
6
|
+
|
|
7
|
+
Related agents: [数据清洗补全](https://github.com/duhu2000/dsh-data-cleaning-agent) · [AI填表](https://github.com/duhu2000/dsh-form-fill-agent) · [访前尽调](https://github.com/duhu2000/dsh-pre-duediligence) · [招投标](https://github.com/duhu2000/dsh-tender-workbench)
|
|
8
|
+
|
|
3
9
|
> A data cleaning & completion agent plugin for DeepSeek Harness: local CSV/XLSX/JSON engine plus optional Qichacha (QCC) MCP enterprise-data enrichment. Initiated and maintained by the Qichacha (QCC) team.
|
|
4
10
|
>
|
|
5
|
-
> Current source version / 当前源码版本: **0.8.
|
|
11
|
+
> Current source version / 当前源码版本: **0.8.15** (stable release)
|
|
6
12
|
|
|
7
13
|
This release fixes misleading import errors after a successful upload. Files are parsed automatically, with persistent source, filename, and row-count status; text parsing handles only newly pasted content. The same file can be selected again, failed parsing preserves existing data, and pending pasted content must be parsed or cleared before continuing. Automatic mapping for 128 fields, blank-cell enrichment in original columns, QCC-blue menus, the resizable workbench, and native DSH sending remain unchanged. Existing download artifacts are not rewritten.
|
|
8
14
|
|
package/README.md
CHANGED
|
@@ -1,8 +1,31 @@
|
|
|
1
1
|
# dsh-data-cleaning-agent
|
|
2
2
|
|
|
3
|
+
本次补丁仅更新搜索发现与安装转化文档,运行时能力保持上一版本;发布记录见 [发布说明](docs/RELEASE-0.8.15.md)。
|
|
4
|
+
|
|
5
|
+
## 安装与三分钟上手
|
|
6
|
+
|
|
7
|
+
数据清洗补全智能体:面向 Excel/CSV/JSON 企业名单,提供数据清洗、表格清洗、清洗补全、去重、企业数据补全与字段补全,支持企查查 MCP 和结果导出。
|
|
8
|
+
|
|
9
|
+
```sh
|
|
10
|
+
dsh plugin --profile web add dsh-data-cleaning-agent@0.8.15
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
请先满足下文的 DSH、连接器及侧边栏依赖要求;安装后完整停止并重启对应 Profile。
|
|
14
|
+
|
|
15
|
+
上传一份合成 CSV(如表头“姓名,手机号,金额”,两行重复的“演示用户,13800000000,100”),选择去重并检查结果,再导出新文件。企业字段补全另需已授权的企查查 MCP;先用本地清洗体验流程。
|
|
16
|
+
|
|
17
|
+
**流程样例(示意,非真实调用结果):** 输入两条相同合成记录 → 选择去重规则 → 预览一条保留记录 → 导出结果。
|
|
18
|
+
|
|
19
|
+
**能力边界:** 本地清洗与企业数据补全是不同步骤;外部事实来自用户授权的数据源,无法确定的主体或字段交给人工复核,不编造企业事实。
|
|
20
|
+
|
|
21
|
+
**升级与回滚:** 升级前停止 Profile 并备份任务目录,记录当前精确版本;使用上面的固定版本命令升级,再完整重启。回滚时将版本号替换为升级前记录的版本,并使用升级前任务目录副本;不以旧版直接读取已迁移任务目录。
|
|
22
|
+
|
|
23
|
+
相关智能体:[数据清洗补全](https://github.com/duhu2000/dsh-data-cleaning-agent) · [AI填表](https://github.com/duhu2000/dsh-form-fill-agent) · [访前尽调](https://github.com/duhu2000/dsh-pre-duediligence) · [招投标](https://github.com/duhu2000/dsh-tender-workbench)
|
|
24
|
+
|
|
25
|
+
|
|
3
26
|
> 在 DeepSeek Harness 中清洗、补全、画像企业名单数据的智能体插件:本地 CSV/XLSX/JSON 引擎 + 可选企查查(Qichacha/QCC)MCP 企业数据补全,由企查查(Qichacha/QCC)团队发起并维护。
|
|
4
27
|
>
|
|
5
|
-
> 当前源码版本 / Current source version: **0.8.
|
|
28
|
+
> 当前源码版本 / Current source version: **0.8.15**(正式版本)
|
|
6
29
|
|
|
7
30
|
本版修复文件上传成功后的导入状态误报:文件选择后自动解析,当前来源、文件名和行数持续显示;文本解析仅处理新粘贴内容。支持重新选择同一文件,解析失败保留现有数据,新粘贴内容解析或清空后再进入下一步。保留 128 字段智能映射、原列补空、企查查蓝菜单、可调宽工作台及 DSH 原生发送机制。历史下载文件不自动改写。
|
|
8
31
|
|
package/marketing/metadata.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
"repository": "duhu2000/dsh-data-cleaning-agent",
|
|
4
4
|
"packageName": "dsh-data-cleaning-agent",
|
|
5
5
|
"npm": {
|
|
6
|
-
"description": "
|
|
6
|
+
"description": "Data cleaning and data enrichment for CSV/XLSX/JSON enterprise lists in DeepSeek Harness, including spreadsheet cleaning, deduplication, profiling, optional Qichacha MCP and exports.",
|
|
7
7
|
"requiredKeywords": [
|
|
8
8
|
"deepseek-harness",
|
|
9
9
|
"deepseek",
|
|
@@ -30,11 +30,26 @@
|
|
|
30
30
|
"ai-tools",
|
|
31
31
|
"llm-tools",
|
|
32
32
|
"ai-agents",
|
|
33
|
-
"agent-skills"
|
|
33
|
+
"agent-skills",
|
|
34
|
+
"data-enrichment",
|
|
35
|
+
"spreadsheet-cleaning",
|
|
36
|
+
"数据清洗补全",
|
|
37
|
+
"数据清洗",
|
|
38
|
+
"清洗补全",
|
|
39
|
+
"表格清洗",
|
|
40
|
+
"企业数据补全",
|
|
41
|
+
"字段补全",
|
|
42
|
+
"data cleaning",
|
|
43
|
+
"data enrichment",
|
|
44
|
+
"spreadsheet cleaning",
|
|
45
|
+
"数据 清洗 补全",
|
|
46
|
+
"数据清洗、补全",
|
|
47
|
+
"企查查MCP",
|
|
48
|
+
"企查查 MCP"
|
|
34
49
|
]
|
|
35
50
|
},
|
|
36
51
|
"github": {
|
|
37
|
-
"description": "
|
|
52
|
+
"description": "Data cleaning and data enrichment for CSV/XLSX/JSON enterprise lists in DeepSeek Harness, including spreadsheet cleaning, deduplication, profiling, optional Qichacha MCP and exports.",
|
|
38
53
|
"topics": [
|
|
39
54
|
"deepseek-harness",
|
|
40
55
|
"deepseek",
|
|
@@ -61,7 +76,9 @@
|
|
|
61
76
|
"ai-tools",
|
|
62
77
|
"llm-tools",
|
|
63
78
|
"ai-agents",
|
|
64
|
-
"agent-skills"
|
|
79
|
+
"agent-skills",
|
|
80
|
+
"data-enrichment",
|
|
81
|
+
"spreadsheet-cleaning"
|
|
65
82
|
]
|
|
66
83
|
},
|
|
67
84
|
"readme": {
|
|
@@ -71,8 +88,8 @@
|
|
|
71
88
|
"ctaEn": "If the plugin helps you clean company lists faster, consider [starring the repository](https://github.com/duhu2000/dsh-data-cleaning-agent/stargazers), [filing an issue](https://github.com/duhu2000/dsh-data-cleaning-agent/issues), or [contributing a fix](CONTRIBUTING.md)."
|
|
72
89
|
},
|
|
73
90
|
"externalListing": {
|
|
74
|
-
"en": "Data cleaning
|
|
75
|
-
"zh": "
|
|
91
|
+
"en": "Data cleaning and data enrichment for CSV/XLSX/JSON enterprise lists in DeepSeek Harness, including spreadsheet cleaning, deduplication, profiling, optional Qichacha MCP and exports.",
|
|
92
|
+
"zh": "数据清洗补全智能体:面向 Excel/CSV/JSON 企业名单,提供数据清洗、表格清洗、清洗补全、去重、企业数据补全与字段补全,支持企查查 MCP 和结果导出。"
|
|
76
93
|
},
|
|
77
94
|
"links": {
|
|
78
95
|
"repository": "https://github.com/duhu2000/dsh-data-cleaning-agent",
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-data-cleaning-agent",
|
|
3
|
-
"version": "0.8.
|
|
4
|
-
"description": "
|
|
3
|
+
"version": "0.8.15",
|
|
4
|
+
"description": "Data cleaning and data enrichment for CSV/XLSX/JSON enterprise lists in DeepSeek Harness, including spreadsheet cleaning, deduplication, profiling, optional Qichacha MCP and exports.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "lib/index.js",
|
|
7
7
|
"exports": {
|
|
@@ -84,7 +84,22 @@
|
|
|
84
84
|
"ai-tools",
|
|
85
85
|
"llm-tools",
|
|
86
86
|
"ai-agents",
|
|
87
|
-
"agent-skills"
|
|
87
|
+
"agent-skills",
|
|
88
|
+
"数据清洗补全",
|
|
89
|
+
"数据清洗",
|
|
90
|
+
"清洗补全",
|
|
91
|
+
"表格清洗",
|
|
92
|
+
"企业数据补全",
|
|
93
|
+
"字段补全",
|
|
94
|
+
"data cleaning",
|
|
95
|
+
"data enrichment",
|
|
96
|
+
"spreadsheet cleaning",
|
|
97
|
+
"数据 清洗 补全",
|
|
98
|
+
"数据清洗、补全",
|
|
99
|
+
"企查查MCP",
|
|
100
|
+
"企查查 MCP",
|
|
101
|
+
"data-enrichment",
|
|
102
|
+
"spreadsheet-cleaning"
|
|
88
103
|
],
|
|
89
104
|
"license": "MIT",
|
|
90
105
|
"repository": {
|