v6ole
144 lines
6.4 KiB
PowerShell
144 lines
6.4 KiB
PowerShell
[CmdletBinding()]
|
||
param(
|
||
[string]$SourceDirectory = (Join-Path $PSScriptRoot '..\skills\telecom-rd-standards\references\source-documents'),
|
||
[switch]$Replace
|
||
)
|
||
|
||
$ErrorActionPreference = 'Stop'
|
||
$sourceDirectory = (Resolve-Path $SourceDirectory).Path
|
||
$titles = @{
|
||
'00-issue-notice' = '关于印发中国电信软件研发规范（修订版）的通知'
|
||
'01-capability-classification' = '中国电信软件研发规范分级分类实施指导意见（修订版）'
|
||
'02-rd-standards-revision-overview' = '软件研发系列规范修订介绍'
|
||
'03-overall-rd-standard' = '中国电信软件研发规范总体规范（修订版）'
|
||
'04-requirements-management' = '中国电信软件研发规范需求管理分册（修订版）'
|
||
'05-database-design' = '中国电信软件研发规范数据库设计分册（修订版）'
|
||
'06-python-coding' = '中国电信软件研发规范编码规范（Python 分册）'
|
||
'07-frontend-coding' = '中国电信软件研发规范编码规范（前端分册）'
|
||
'08-code-management' = '中国电信软件研发规范代码管理分册（修订版）'
|
||
'09-artifact-management' = '中国电信软件研发规范制品管理分册（修订版）'
|
||
'10-pipeline-management' = '中国电信软件研发规范流水线管理分册（修订版）'
|
||
'11-test-management' = '中国电信软件研发规范测试管理分册（修订版）'
|
||
'12-security' = '中国电信软件研发规范安全分册（修订版）'
|
||
'13-deployment' = '中国电信软件研发规范部署管理分册'
|
||
'20-rd-cloud-overview' = '研发云平台互联互通规范总册（试行稿）'
|
||
'21-rd-cloud-system-access-auth' = '研发云互联互通规范系统接入技术规范（用户认证和资产授权）（试行稿）'
|
||
'22-rd-cloud-data-open-access' = '研发云互联互通规范数据开放和接入技术规范（试行稿）'
|
||
'23-rd-cloud-openapi' = '研发云互联互通规范能力开放技术规范（OpenAPI 接口）（试行稿）'
|
||
'24-rd-cloud-scaffold-service' = '研发云互联互通规范服务接入技术规范（脚手架服务）（试行稿）'
|
||
}
|
||
|
||
function Test-StructuralLine([string]$Line) {
|
||
return $Line -match '^(\d+(\.\d+){0,4}\s+\S+|第[一二三四五六七八九十]+[章节]|[一二三四五六七八九十]+、|\d+[)）]|[-*•]\s+|[A-Za-z][)）]\s+|[{}\[\]`]|"|//)'
|
||
}
|
||
|
||
function Join-Paragraph([string]$Left, [string]$Right) {
|
||
if ([string]::IsNullOrEmpty($Left)) { return $Right }
|
||
if ($Left -match '[A-Za-z0-9]$' -and $Right -match '^[A-Za-z0-9]') { return "$Left $Right" }
|
||
return "$Left$Right"
|
||
}
|
||
|
||
function Write-Buffer([System.Collections.Generic.List[string]]$Output, [string]$Buffer) {
|
||
if (-not [string]::IsNullOrWhiteSpace($Buffer)) {
|
||
$Output.Add($Buffer)
|
||
$Output.Add('')
|
||
}
|
||
}
|
||
|
||
$txtFiles = Get-ChildItem -LiteralPath $sourceDirectory -File -Filter '*.txt'
|
||
if ($txtFiles.Count -eq 0) {
|
||
throw "No TXT documents found in $sourceDirectory."
|
||
}
|
||
|
||
foreach ($txtFile in $txtFiles) {
|
||
$baseName = [System.IO.Path]::GetFileNameWithoutExtension($txtFile.Name)
|
||
$title = $titles[$baseName]
|
||
if (-not $title) { $title = $baseName }
|
||
$output = [System.Collections.Generic.List[string]]::new()
|
||
$output.Add("# $title")
|
||
$output.Add('')
|
||
$output.Add('> 脱敏整理版：已移除编制人员、联系人和联系方式，并合并无意义硬换行。技术条款、章节和示例以原始 DOCX 为争议核验依据。')
|
||
$output.Add('')
|
||
|
||
$buffer = ''
|
||
$skipAuthorMetadata = $false
|
||
$skipContactLines = 0
|
||
foreach ($rawLine in Get-Content -LiteralPath $txtFile.FullName) {
|
||
$line = ($rawLine -replace '[\u00A0\t]+', ' ' -replace '\s{2,}', ' ').Trim()
|
||
|
||
if ($skipContactLines -gt 0) {
|
||
$skipContactLines--
|
||
continue
|
||
}
|
||
if ($line -match '^(规范编制人员|编制人员)(：|:)?') {
|
||
Write-Buffer $output $buffer
|
||
$buffer = ''
|
||
$output.Add('> 编制人员信息已移除。')
|
||
$output.Add('')
|
||
$skipAuthorMetadata = $true
|
||
continue
|
||
}
|
||
if ($skipAuthorMetadata) {
|
||
if ($line -match '^(版本变更历史|目录|\d+(\.\d+){0,4}\s+\S+)') {
|
||
$skipAuthorMetadata = $false
|
||
} elseif ([string]::IsNullOrWhiteSpace($line)) {
|
||
continue
|
||
} else {
|
||
continue
|
||
}
|
||
}
|
||
if ($line -match '^(评审人员|传阅人员|审阅人员|审核人员)[:：]') {
|
||
Write-Buffer $output $buffer
|
||
$buffer = ''
|
||
$output.Add('> 评审与传阅人员信息已移除。')
|
||
$output.Add('')
|
||
continue
|
||
}
|
||
if ($line -match '联系人[:：]?$' -or $line -match '^如有问题.*联系人') {
|
||
Write-Buffer $output $buffer
|
||
$buffer = ''
|
||
$output.Add('> 联系方式已移除。')
|
||
$output.Add('')
|
||
$skipContactLines = 2
|
||
continue
|
||
}
|
||
|
||
$line = $line -replace '(?<!\d)1[3-9]\d{9}(?!\d)', '[手机号已脱敏]'
|
||
$line = $line -replace '(?i)[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}', '[邮箱已脱敏]'
|
||
$line = $line -replace '张三', '示例创建人'
|
||
|
||
if ([string]::IsNullOrWhiteSpace($line)) {
|
||
Write-Buffer $output $buffer
|
||
$buffer = ''
|
||
continue
|
||
}
|
||
|
||
if (Test-StructuralLine $line) {
|
||
Write-Buffer $output $buffer
|
||
$buffer = ''
|
||
if ($line -match '^(\d+(\.\d+)*)\s+(.+)$' -and $line -notmatch '【强制】') {
|
||
$depth = ([regex]::Matches($Matches[1], '\.').Count + 2)
|
||
$depth = [Math]::Min($depth, 6)
|
||
$output.Add(('#' * $depth) + ' ' + $line)
|
||
} elseif ($line -match '^(第[一二三四五六七八九十]+[章节]|[一二三四五六七八九十]+、)') {
|
||
$output.Add('## ' + $line)
|
||
} else {
|
||
$output.Add($line)
|
||
}
|
||
$output.Add('')
|
||
continue
|
||
}
|
||
|
||
$buffer = Join-Paragraph $buffer $line
|
||
}
|
||
Write-Buffer $output $buffer
|
||
|
||
$markdownPath = Join-Path $sourceDirectory "$baseName.md"
|
||
[System.IO.File]::WriteAllText($markdownPath, (($output -join [Environment]::NewLine).TrimEnd() + [Environment]::NewLine), [System.Text.UTF8Encoding]::new($false))
|
||
if ($Replace) {
|
||
Remove-Item -LiteralPath $txtFile.FullName
|
||
}
|
||
}
|
||
|
||
Write-Output "Converted $($txtFiles.Count) TXT documents to Markdown. Replace=$Replace"
|