wukong-gitlog-cli 1.0.35 → 1.0.36

package/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
 
+### [1.0.36](https://github.com/tomatobybike/wukong-gitlog-cli/compare/v1.0.35...v1.0.36) (2025-12-12)
+
+
+### Bug Fixes
+
+* 🐛 createAuthorNormalizer ([12f70ba](https://github.com/tomatobybike/wukong-gitlog-cli/commit/12f70ba10013cbba988d3ae1d7fed6f0949c6cbc))
+
 ### [1.0.35](https://github.com/tomatobybike/wukong-gitlog-cli/compare/v1.0.34...v1.0.35) (2025-12-12)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wukong-gitlog-cli",
-  "version": "1.0.35",
+  "version": "1.0.36",
   "description": "Advanced Git commit log exporter with Excel/JSON/TXT output, grouping, stats and CLI.",
   "keywords": [
     "git",

package/src/git.mjs

@@ -166,7 +166,10 @@ export async function getGitLogsQuick(opts) {
   }
 }
 
-export async function getGitLogsFast(opts) {
+/**
+ * 高性能 git log + numstat 获取 commit
+ */
+export async function getGitLogsFast(opts = {}) {
   const { author, email, since, until, limit, merges } = opts
 
   const pretty = `${[
@@ -174,16 +177,11 @@ export async function getGitLogsFast(opts) {
     '%an', // author name
     '%ae', // email
     '%ad', // date
-    '%s', // subject
-    '%B' // body
-  ].join('%x1f')}%x1e`
+    '%s',  // subject
+    '%B'   // body
+  ].join('%x1f')  }%x1e`
 
-  const args = [
-    'log',
-    `--pretty=format:${pretty}`,
-    '--date=iso-local',
-    '--numstat'
-  ]
+  const args = ['log', `--pretty=format:${pretty}`, '--date=iso-local', '--numstat']
 
   if (author) args.push(`--author=${author}`)
   if (email) args.push(`--author=${email}`)
@@ -193,21 +191,18 @@ export async function getGitLogsFast(opts) {
   if (limit) args.push('-n', `${limit}`)
 
   const { stdout } = await $`git ${args}`.quiet()
+  const raw = stdout.replace(/\r/g, '')
 
   const commits = []
-  const raw = stdout.replace(/\r/g, '')
 
-  // 正则匹配每个 commit header + numstat
-  const commitRegex =
-    // eslint-disable-next-line no-control-regex
-    /([0-9a-f]+)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([\s\S]*?)(?=(?:[0-9a-f]{7,40}\x1f)|\x1e$)/g
+  // 匹配每个 commit header + numstat
+  // eslint-disable-next-line no-control-regex
+  const commitRegex = /([0-9a-f]+)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([\s\S]*?)(?=(?:[0-9a-f]{7,40}\x1f)|\x1e$)/g
   let match
-  // eslint-disable-next-line no-cond-assign
-  while ((match = commitRegex.exec(raw)) !== null) {
-    const [_, hash, authorName, emailAddr, date, subject, bodyAndNumstat] =
-      match
-    const [, changeId] =
-      bodyAndNumstat.match(/Change-Id:\s*(I[0-9a-fA-F]+)/) || []
+
+  for (const ns of raw.matchAll(commitRegex)) {
+    const [_, hash, authorName, emailAddr, date, subject, bodyAndNumstat] = ns
+    const [, changeId] = bodyAndNumstat.match(/Change-Id:\s*(I[0-9a-fA-F]+)/) || []
 
     const c = {
       hash,
@@ -224,13 +219,12 @@ export async function getGitLogsFast(opts) {
       files: []
     }
 
-    // 匹配 numstat 行
+    // 匹配 numstat
     const numstatRegex = /^(\d+)\s+(\d+)\s+(.+)$/gm
-
-    for (const nsMatch of bodyAndNumstat.matchAll(numstatRegex)) {
-      const added = parseInt(nsMatch[1], 10) || 0
-      const deleted = parseInt(nsMatch[2], 10) || 0
-      const file = nsMatch[3]
+    for (const m of bodyAndNumstat.matchAll(numstatRegex)) {
+      const added = parseInt(m[1], 10) || 0
+      const deleted = parseInt(m[2], 10) || 0
+      const file = m[3]
       c.added += added
       c.deleted += deleted
       c.changed += added + deleted
@@ -240,8 +234,17 @@ export async function getGitLogsFast(opts) {
     commits.push(c)
   }
 
+  // 最终统一覆盖 author，保证所有 commit 都使用中文名（如存在）
+  const finalMap = normalizer.getMap()
+  for (const c of commits) {
+    if (c.email && finalMap[c.email]) {
+      c.author = finalMap[c.email]
+    }
+  }
+
   return {
     commits,
-    authorMap: normalizer.getMap()
+    authorMap: finalMap,
+    originalMap: normalizer.getOriginalMap()
   }
 }

package/src/utils/authorNormalizer.mjs

@@ -1,26 +1,20 @@
-// authorNormalizer.js
 /**
  * 按邮箱自动归一化作者名字
- * - 优先使用中文姓名
- * - 如果同邮箱出现多个非中文名，保持第一个
- * - 自动清理空格与不可见字符
+ * - 中文名优先覆盖
+ * - 同邮箱多个英文名保持第一个
  * - 保留原始 author 以便 debug
  */
 export function createAuthorNormalizer() {
   const map = {} // email -> canonical name
-  const originalMap = {} // email -> 原始所有 author 名
+  const originalMap = {} // email -> Set of original author names
 
   function isChinese(str) {
     return /[\u4e00-\u9fa5]/.test(str)
   }
 
   function cleanName(str) {
-    if (!str) return ''
-    return str
-      // eslint-disable-next-line no-misleading-character-class
-      .replace(/[\u200B\u200C\u200D\uFEFF]/g, '') // 去零宽空格
-      .replace(/\s+/g, ' ') // 多空格 -> 单空格
-      .trim()
+    // eslint-disable-next-line no-misleading-character-class
+    return (str || '').replace(/[\u200B\u200C\u200D\uFEFF]/g, '').trim()
   }
 
   function cleanEmail(str) {
@@ -28,31 +22,30 @@ export function createAuthorNormalizer() {
   }
 
   function getAuthor(name, email) {
-    const cleanedName = cleanName(name)
-    const cleanedEmail = cleanEmail(email)
+    const n = cleanName(name)
+    const e = cleanEmail(email)
 
-    if (!cleanedEmail) return cleanedName || 'Unknown'
+    if (!e) return n || 'Unknown'
 
-    // 记录原始 author 便于 debug
-    if (!originalMap[cleanedEmail]) originalMap[cleanedEmail] = new Set()
-    if (cleanedName) originalMap[cleanedEmail].add(cleanedName)
+    // 记录原始 author
+    if (!originalMap[e]) originalMap[e] = new Set()
+    if (n) originalMap[e].add(n)
 
-    const canonical = map[cleanedEmail]
+    const prev = map[e]
 
-    // 首次遇到这个邮箱 → 记录当前作者名
-    if (!canonical) {
-      map[cleanedEmail] = cleanedName || cleanedEmail
-      return map[cleanedEmail]
+    // 中文名优先覆盖
+    if (isChinese(n)) {
+      map[e] = n
+      return n
     }
 
-    // 新名是中文 → 覆盖旧的
-    if (isChinese(cleanedName)) {
-      map[cleanedEmail] = cleanedName
-      return map[cleanedEmail]
-    }
+    // 已有中文名 → 返回中文
+    if (prev && isChinese(prev)) return prev
+
+    // 首次出现英文名 → 记录
+    if (!prev) map[e] = n
 
-    // 新名非中文 → 保留已有中文或旧名
-    return canonical
+    return map[e]
   }
 
   return {