# 词根盘点标注脚本:为 01/02/03 词条打 ✅(已收录)/ ⭐(新词)标注并统计 $ErrorActionPreference = 'Stop' $base = 'D:\考研\英语' $coveredPath = Join-Path $base '_vcb_covered.txt' $folder = Join-Path $base '英语词汇\词根盘点' $files = @( '01-同根异义·一个词根十个面孔.md', '02-形近异源·假同根与同源双词.md', '03-同形多义·一词多义与同形异义速查.md' ) $readme = Join-Path $folder 'README-总览与复习指引.md' # 1. 读覆盖词表(全表 38 组 + 法律政治专题,去重 3734 词) $covered = New-Object 'System.Collections.Generic.HashSet[string]' ([System.StringComparer]::OrdinalIgnoreCase) foreach ($line in [System.IO.File]::ReadAllLines($coveredPath, [System.Text.Encoding]::UTF8)) { $w = $line.Trim() if ($w -ne '') { [void]$covered.Add($w) } } # 2. 逐文件标注 + 统计 $stats = @{} foreach ($f in $files) { $path = Join-Path $folder $f $text = [System.IO.File]::ReadAllText($path, [System.Text.Encoding]::UTF8) $allWords = New-Object 'System.Collections.Generic.HashSet[string]' ([System.StringComparer]::OrdinalIgnoreCase) $coveredWords = New-Object 'System.Collections.Generic.HashSet[string]' ([System.StringComparer]::OrdinalIgnoreCase) $newWords = New-Object 'System.Collections.Generic.HashSet[string]' ([System.StringComparer]::OrdinalIgnoreCase) $evaluator = [System.Text.RegularExpressions.MatchEvaluator]{ param($m) $word = $m.Groups[1].Value.Trim() if ($word -eq '') { return $m.Value } [void]$allWords.Add($word) if ($covered.Contains($word)) { [void]$coveredWords.Add($word) return "**$word**✅" } else { [void]$newWords.Add($word) return "**$word**⭐" } } $newText = [regex]::Replace($text, '\{\{([^}]+)\}\}', $evaluator) # 追加标注统计脚注(幂等:先移除旧的统计块) $footerMark = "## 本文件标注统计(由脚本生成)" $idx = $newText.IndexOf($footerMark) if ($idx -ge 0) { $newText = $newText.Substring(0, $idx).TrimEnd() + "`r`n" } $total = $allWords.Count $cov = $coveredWords.Count $new = $newWords.Count $stats[$f] = @{ total = $total; covered = $cov; news = $new } $footer = @" $footerMark - 词条总数(去重):$total - ✅ 已收录(词汇全表+法律政治专题):$cov - ⭐ 新词(建议补录):$new "@ $newText = $newText.TrimEnd() + $footer [System.IO.File]::WriteAllText($path, $newText, (New-Object System.Text.UTF8Encoding($false))) Write-Output ("{0} total={1} covered={2} new={3}" -f $f, $total, $cov, $new) } # 3. 更新 README 统计表 $rt = [System.IO.File]::ReadAllText($readme, [System.Text.Encoding]::UTF8) foreach ($f in $files) { $name = $f -replace '\.md$','' $s = $stats[$f] $row = "| $name | $($s.covered) | $($s.news) | $($s.total) |" # 替换该文件名开头的统计行 $rt = [regex]::Replace($rt, "(?m)^\|\s*$([regex]::Escape($name))\s*\|[^\r\n]*$", $row) } [System.IO.File]::WriteAllText($readme, $rt, (New-Object System.Text.UTF8Encoding($false))) Write-Output 'README stats updated.'