wukong-gitlog-cli 1.0.33 → 1.0.35

package/CHANGELOG.md

@@ -2,6 +2,20 @@
 
 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.
 
+### [1.0.35](https://github.com/tomatobybike/wukong-gitlog-cli/compare/v1.0.34...v1.0.35) (2025-12-12)
+
+
+### Features
+
+* 🎸 createAuthorNormalizer ([a23a80e](https://github.com/tomatobybike/wukong-gitlog-cli/commit/a23a80e6d664cc5db89b40a63456d8e8d4b2c321))
+
+### [1.0.34](https://github.com/tomatobybike/wukong-gitlog-cli/compare/v1.0.33...v1.0.34) (2025-12-12)
+
+
+### Bug Fixes
+
+* 🐛 eslint error ([3d48e25](https://github.com/tomatobybike/wukong-gitlog-cli/commit/3d48e25eb1217005ac2a525b54e307ca328b85e7))
+
 ### [1.0.33](https://github.com/tomatobybike/wukong-gitlog-cli/compare/v1.0.32...v1.0.33) (2025-12-12)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wukong-gitlog-cli",
-  "version": "1.0.33",
+  "version": "1.0.35",
   "description": "Advanced Git commit log exporter with Excel/JSON/TXT output, grouping, stats and CLI.",
   "keywords": [
     "git",

package/src/cli.mjs

@@ -14,7 +14,7 @@ import {
   exportExcelAuthorChangeStats,
   exportExcelPerPeriodSheets
 } from './excel.mjs'
-import { getGitLogs } from './git.mjs'
+import { getGitLogsFast } from './git.mjs'
 import { renderAuthorChangesJson } from './json.mjs'
 import {
   analyzeOvertime,
@@ -22,6 +22,7 @@ import {
   renderOvertimeTab,
   renderOvertimeText
 } from './overtime.mjs'
+import { renderAuthorMapText } from './renderAuthorMapText.mjs'
 import { startServer } from './server.mjs'
 import { renderChangedLinesText, renderText } from './text.mjs'
 import { checkUpdateWithPatch } from './utils/checkUpdate.mjs'
@@ -203,8 +204,9 @@ const main = async () => {
 
   const spinner = ora('Loading...').start()
 
-  let records = await getGitLogs(opts)
-
+  const gitCommits = await getGitLogsFast(opts)
+  let { commits: records } = gitCommits
+  const { authorMap } = gitCommits
   // compute output directory root if user provided one or wants parent
 
   // --- Gerrit 地址处理（若提供） ---
@@ -319,6 +321,11 @@ const main = async () => {
     // Output to console
     console.log('\n--- Overtime analysis ---\n')
     console.log(renderOvertimeText(stats))
+
+    const authorMapText = renderAuthorMapText(authorMap)
+    console.log('\n Developers:\n', authorMapText, '\n')
+    writeTextFile(outputFilePath('authors.text', outDir), authorMapText)
+    
     // if user requested json format, write stats to file
     if (opts.json || opts.format === 'json') {
       const file = opts.out || 'overtime.json'
@@ -352,7 +359,10 @@ const main = async () => {
         const commitsModule = `export default ${JSON.stringify(records, null, 2)};\n`
         writeTextFile(dataCommitsFile, commitsModule)
 
-        const dataCommitsChangedFile = outputFilePath('data/author-changes.mjs', outDir)
+        const dataCommitsChangedFile = outputFilePath(
+          'data/author-changes.mjs',
+          outDir
+        )
         const jsonText = renderAuthorChangesJson(records)
 
         const commitsChangedModule = `export default ${JSON.stringify(jsonText, null, 2)};\n`
@@ -802,6 +812,7 @@ const main = async () => {
       outputFilePath('author-changes.text', outDir),
       renderChangedLinesText(records)
     )
+
     console.log(text)
     console.log(chalk.green(`文本已导出: ${filepath}`))
     spinner.succeed('Done')

package/src/git.mjs

@@ -1,6 +1,10 @@
 import { $ } from 'zx'
 
-export async function getGitLogs(opts) {
+import { createAuthorNormalizer } from './utils/authorNormalizer.mjs'
+
+const normalizer = createAuthorNormalizer()
+
+export async function getGitLogsSlow(opts) {
   const { author, email, since, until, limit, merges } = opts
 
   const pretty = '%H%x1f%an%x1f%ae%x1f%ad%x1f%s%x1f%B%x1e'
@@ -31,7 +35,8 @@ export async function getGitLogs(opts) {
 
       return {
         hash,
-        author: authorName,
+        author: normalizer.getAuthor(authorName, emailAddr),
+        originalAuthor: authorName,
         email: emailAddr,
         date,
         message: subject,
@@ -43,7 +48,8 @@ export async function getGitLogs(opts) {
   // === 新增：为每个 commit 计算代码增量 ===
   for (const c of commits) {
     try {
-      const { stdout: diffOut } = await $`git show --numstat --format= ${c.hash}`.quiet()
+      const { stdout: diffOut } =
+        await $`git show --numstat --format= ${c.hash}`.quiet()
       // numstat 格式:  "12 5 path/file.js"
       const lines = diffOut
         .split('\n')
@@ -72,3 +78,170 @@ export async function getGitLogs(opts) {
 
   return commits
 }
+
+export async function getGitLogsQuick(opts) {
+  const { author, email, since, until, limit, merges } = opts
+
+  const pretty =
+    `${[
+      '%H', // hash
+      '%an', // author name
+      '%ae', // email
+      '%ad', // date
+      '%s', // subject
+      '%B' // body
+    ].join('%x1f')  }%x1e`
+
+  const args = [
+    'log',
+    `--pretty=format:${pretty}`,
+    '--date=iso-local',
+    '--numstat'
+  ]
+
+  if (author) args.push(`--author=${author}`)
+  if (email) args.push(`--author=${email}`)
+  if (since) args.push(`--since=${since}`)
+  if (until) args.push(`--until=${until}`)
+  if (merges === false) args.push(`--no-merges`)
+  if (limit) args.push('-n', `${limit}`)
+
+  const { stdout } = await $`git ${args}`.quiet()
+
+  const rawCommits = stdout.split('\x1e').filter(Boolean)
+  const commits = []
+
+  for (const raw of rawCommits) {
+    const block = raw.replace(/\r/g, '').trim()
+    // eslint-disable-next-line no-continue
+    if (!block) continue
+
+    // header: 6 个字段用 \x1f 分隔
+    const headerMatch = block.match(
+      // eslint-disable-next-line no-control-regex
+      /^([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([\s\S]*)$/
+    )
+    // eslint-disable-next-line no-continue
+    if (!headerMatch) continue
+
+    const [, hash, authorName, emailAddr, date, subject, body] = headerMatch
+
+    const [, changeId] = body.match(/Change-Id:\s*(I[0-9a-fA-F]+)/) || []
+
+    const c = {
+      hash,
+      author: normalizer.getAuthor(authorName, emailAddr),
+      originalAuthor: authorName,
+      email: emailAddr,
+      date,
+      message: subject,
+      body,
+      changeId,
+      added: 0,
+      deleted: 0,
+      changed: 0,
+      files: []
+    }
+
+    // 匹配所有 numstat 行
+    const numstatLines = block
+      .split('\n')
+      .filter((l) => /^\d+\s+\d+\s+/.test(l))
+    for (const line of numstatLines) {
+      const [a, d, file] = line.trim().split(/\s+/)
+      const added = parseInt(a, 10) || 0
+      const deleted = parseInt(d, 10) || 0
+      c.added += added
+      c.deleted += deleted
+      c.changed += added + deleted
+      c.files.push({ file, added, deleted })
+    }
+
+    commits.push(c)
+  }
+
+  return {
+    commits,
+    authorMap: normalizer.getMap()
+  }
+}
+
+export async function getGitLogsFast(opts) {
+  const { author, email, since, until, limit, merges } = opts
+
+  const pretty = `${[
+    '%H', // hash
+    '%an', // author name
+    '%ae', // email
+    '%ad', // date
+    '%s', // subject
+    '%B' // body
+  ].join('%x1f')}%x1e`
+
+  const args = [
+    'log',
+    `--pretty=format:${pretty}`,
+    '--date=iso-local',
+    '--numstat'
+  ]
+
+  if (author) args.push(`--author=${author}`)
+  if (email) args.push(`--author=${email}`)
+  if (since) args.push(`--since=${since}`)
+  if (until) args.push(`--until=${until}`)
+  if (merges === false) args.push(`--no-merges`)
+  if (limit) args.push('-n', `${limit}`)
+
+  const { stdout } = await $`git ${args}`.quiet()
+
+  const commits = []
+  const raw = stdout.replace(/\r/g, '')
+
+  // 正则匹配每个 commit header + numstat
+  const commitRegex =
+    // eslint-disable-next-line no-control-regex
+    /([0-9a-f]+)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([^\x1f]*)\x1f([\s\S]*?)(?=(?:[0-9a-f]{7,40}\x1f)|\x1e$)/g
+  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]+)/) || []
+
+    const c = {
+      hash,
+      author: normalizer.getAuthor(authorName, emailAddr),
+      originalAuthor: authorName,
+      email: emailAddr,
+      date,
+      message: subject,
+      body: bodyAndNumstat,
+      changeId,
+      added: 0,
+      deleted: 0,
+      changed: 0,
+      files: []
+    }
+
+    // 匹配 numstat 行
+    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]
+      c.added += added
+      c.deleted += deleted
+      c.changed += added + deleted
+      c.files.push({ file, added, deleted })
+    }
+
+    commits.push(c)
+  }
+
+  return {
+    commits,
+    authorMap: normalizer.getMap()
+  }
+}

package/src/renderAuthorMapText.mjs

@@ -0,0 +1,21 @@
+/**
+ * 输出 authorMap 映射表文本
+ * @param {Record<string,string>} authorMap - email -> normalized author name
+ * @param {Object} opts
+ * @param {boolean} opts.showHeader - 是否显示表头
+ * @returns {string} 文本内容
+ */
+export function renderAuthorMapText(authorMap, opts = {}) {
+  const { showHeader = true } = opts
+  const pad = (s, n) => (s.length >= n ? `${s.slice(0, n - 1)}…` : s + ' '.repeat(n - s.length))
+
+  const header = showHeader ? `${pad('Email', 30)} | ${pad('Author', 20)}` : ''
+  const line = showHeader ? '-'.repeat(header.length) : ''
+
+  const rows = []
+  for (const [email, author] of Object.entries(authorMap)) {
+    rows.push(`${pad(email, 30)} | ${pad(author, 20)}`)
+  }
+
+  return showHeader ? [header, line, ...rows].join('\n') : rows.join('\n')
+}

package/src/text.mjs

@@ -3,8 +3,10 @@ import { buildAuthorChangeStats } from './stats.mjs'
 
 export function renderText(records, groups = null, opts = {}) {
   const { showGerrit = false } = opts
-  const pad = (s, n) =>
-    s.length >= n ? `${s.slice(0, n - 1)}…` : s + ' '.repeat(n - s.length)
+  const pad = (s, n) => {
+    return s.length >= n ? `${s.slice(0, n - 1)}…` : s + ' '.repeat(n - s.length)
+  }
+
 
   const baseHeader = `${pad('Hash', 10)} | ${pad('Author', 18)} | ${pad(
     'Date',

package/src/utils/authorNormalizer.mjs

@@ -0,0 +1,69 @@
+// 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
+ * - 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
+
+  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()
+  }
+
+  function cleanEmail(str) {
+    return (str || '').trim()
+  }
+
+  function getAuthor(name, email) {
+    const cleanedName = cleanName(name)
+    const cleanedEmail = cleanEmail(email)
+
+    if (!cleanedEmail) return cleanedName || 'Unknown'
+
+    // 记录原始 author 便于 debug
+    if (!originalMap[cleanedEmail]) originalMap[cleanedEmail] = new Set()
+    if (cleanedName) originalMap[cleanedEmail].add(cleanedName)
+
+    const canonical = map[cleanedEmail]
+
+    // 首次遇到这个邮箱 → 记录当前作者名
+    if (!canonical) {
+      map[cleanedEmail] = cleanedName || cleanedEmail
+      return map[cleanedEmail]
+    }
+
+    // 新名是中文 → 覆盖旧的
+    if (isChinese(cleanedName)) {
+      map[cleanedEmail] = cleanedName
+      return map[cleanedEmail]
+    }
+
+    // 新名非中文 → 保留已有中文或旧名
+    return canonical
+  }
+
+  return {
+    getAuthor,
+    getMap: () => map,
+    getOriginalMap: () => {
+      const res = {}
+      for (const [email, names] of Object.entries(originalMap)) {
+        res[email] = Array.from(names)
+      }
+      return res
+    }
+  }
+}