From eff4a278dea6067df8d1e84a7e659c1d2560c904 Mon Sep 17 00:00:00 2001
From: Dnomd343 <i@343.re>
Date: Tue, 6 Dec 2022 15:20:13 +0800
Subject: [PATCH] docs: update README.md

---
 README.md | 57 +++++++++++++++++++++++++++++++------------------------
 1 file changed, 32 insertions(+), 25 deletions(-)

diff --git a/README.md b/README.md
index 4a0795b..e0b8181 100644
--- a/README.md
+++ b/README.md
@@ -23,6 +23,11 @@
         s3_fixed(sample_3)
       end
 
+      subgraph release
+        sa{{sample_a}}
+        sb{{sample_b}}
+      end
+
       s1a_raw -- replenish --> s1_combine
       s1b_raw --> s1_combine
       s2a_raw -- replenish --> s2_combine
@@ -32,6 +37,11 @@
       s1_combine -- fix --> s1_fixed
       s2_combine -- fix --> s2_fixed
       s3_combine -- fix --> s3_fixed
+
+      s1_fixed --> sa
+      s2_fixed -- replenish --> sa
+      s2_fixed -. restore .-> sb
+      s3_fixed -- replenish --> sb
     end
 
     subgraph crawler
@@ -44,16 +54,9 @@
       source_7([zhihu.com]) --> s3_raw
     end
 
-    subgraph release
-      sa{{sample_a}}
-      sb{{sample_b}}
+    subgraph rc
       rc-1(rc-1)
 
-      s1_fixed --> sa
-      s2_fixed -- replenish --> sa
-      s2_fixed -. restore .-> sb
-      s3_fixed -- replenish --> sb
-
       sa --> rc-1
       sb -- fix --> rc-1
     end
@@ -61,47 +64,51 @@
 
 ## 数据爬虫来源
 
-+ [`108shu.com`](./src/crawler/108shu.com) ：[`http://www.108shu.com/book/54247/`](http://www.108shu.com/book/54247/)
++ [`108shu.com`](./src/crawler/108shu.com) ：[http://www.108shu.com/book/54247/](http://www.108shu.com/book/54247/)
 
-+ [`aidusk.com`](./src/crawler/aidusk.com) ：[`http://www.aidusk.com/t/134659/`](http://www.aidusk.com/t/134659/)
++ [`aidusk.com`](./src/crawler/aidusk.com) ：[http://www.aidusk.com/t/134659/](http://www.aidusk.com/t/134659/)
 
-+ [`ixsw.la`](./src/crawler/ixsw.la) ：[`https://www.ixsw.la/ks82668/`](https://www.ixsw.la/ks82668/)
++ [`ixsw.la`](./src/crawler/ixsw.la) ：[https://www.ixsw.la/ks82668/](https://www.ixsw.la/ks82668/)
 
-+ [`m.wxsy.net`](./src/crawler/m.wxsy.net) ：[`https://m.wxsy.net/novel/57104/`](https://m.wxsy.net/novel/57104/)
++ [`m.wxsy.net`](./src/crawler/m.wxsy.net) ：[https://m.wxsy.net/novel/57104/](https://m.wxsy.net/novel/57104/)
 
-+ [`wxsy.net`](./src/crawler/wxsy.net) ：[`https://www.wxsy.net/novel/57104/`](https://www.wxsy.net/novel/57104/)
++ [`wxsy.net`](./src/crawler/wxsy.net) ：[https://www.wxsy.net/novel/57104/](https://www.wxsy.net/novel/57104/)
 
-+ [`xswang.com`](./src/crawler/xswang.com) ：[`https://www.xswang.com/book/56718/`](https://www.xswang.com/book/56718/)
++ [`xswang.com`](./src/crawler/xswang.com) ：[https://www.xswang.com/book/56718/](https://www.xswang.com/book/56718/)
 
-+ [`zhihu.com`](./src/crawler/zhihu.com) ：[`https://www.zhihu.com/column/c_1553471910075449344`](https://www.zhihu.com/column/c_1553471910075449344)
++ [`zhihu.com`](./src/crawler/zhihu.com) ：[https://www.zhihu.com/column/c_1553471910075449344](https://www.zhihu.com/column/c_1553471910075449344)
 
 
 ## 爬虫样本分析
 
 原始爬虫得到5份三组不同 `raw` 数据：
 
-+ sample_1-a
++ `sample_1-a`
 
-+ sample_1-b
++ `sample_1-b`
 
-+ sample_2-a
++ `sample_2-a`
 
-+ sample_2-b
++ `sample_2-b`
 
-+ sample_3
++ `sample_3`
 
 经过简单合并后可得到三份初始 `combine` 样本：
 
-+ sample_1
++ `sample_1`
 
-+ sample_2
++ `sample_2`
 
-+ sample_3
++ `sample_3`
 
 三份样本进行对照合并，修复各类语法词汇错误、违禁屏蔽词等，得到最终的三组 `fixed` 样本，而后对其合并，获得两组 `release` 样本：
 
-+ sample_a
++ `sample_a`
 
-+ sample_b
++ `sample_b`
 
 两组样本只有微小的分隔区别，经过修复合并后得到 `RC` 样本。
+
+## 数据发布
+
++ `RC-1` ：初始合并版本