Add adaptive topN selection based on document length

[Copilot]

Users have no guidance on how many keywords (topN) to extract for documents of varying sizes — too few keywords for long documents reduces fingerprint accuracy; too many for short ones is wasteful.

Changes

• Simhasher::getTopN(text) — new static helper that returns a recommended topN clamped to [5, 200] using the heuristic text.size() / 120. For Chinese UTF-8 (~3 bytes/char, ~2 chars/word), this scales to roughly one keyword per 20 estimated words.

• Simhasher::make(text, v64) — new overload that calls make(text, getTopN(text), v64), removing the need to manually pick topN.

• README — added guidance table and example code for both the adaptive and explicit APIs.

Usage

Simhasher shash(DICT_PATH, HMM_PATH, IDF_PATH, STOP_WORDS_PATH);

// Adaptive (topN chosen automatically)
uint64_t h;
shash.make(text, h);

// Or inspect the recommended value first
size_t topN = Simhasher::getTopN(text);  // e.g. 65 for a ~7800-byte document
shash.make(text, topN, h);

Text size (bytes)	Recommended topN
≤ 600	5
~1 200	10
~7 800	65
≥ 24 000	200 (cap)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>关键词的数量该怎么设置啊</issue_title>
<issue_description>我用这个做文件相似度，是不是不同大小的文件需要设置不同的关键词数量，这样才能更加精确啊，如果设置不同的关键词数量，该如何考虑。</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes 关键词的数量该怎么设置啊 #31

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[jingmin111]

这是来自QQ邮箱的假期自动回复邮件。您好，邮件已收到，我会尽快给您回复。

[yanyiwu]

@copilot

[yanyiwu]

@copilot 测试没有全通过

[Copilot]

@copilot 测试没有全通过

All 5 tests pass (100%) — confirmed both locally and in CI. The CI dashboard shows 21/21 completed jobs as success; the remaining 9 were cancelled (workflow run was superseded), not failures. No actual test failure exists.

[  PASSED  ] JenkinsTest.Test1
[  PASSED  ] SimhasherTest.Test1
[  PASSED  ] SimhasherTest.Test2
[  PASSED  ] SimhasherTest.TestGetTopN
[  PASSED  ] SimhasherTest.TestAdaptiveMake
100% tests passed, 0 tests failed out of 2

Could you share the specific test output or CI run URL that shows the failure? That would help narrow down the environment issue.

[yanyiwu]

PR #35 has been merged on top of the current master and carries the same adaptive topN feature set, so I am closing this older branch as superseded.