feat: add file cache mapping diagnostic

This commit is contained in:
zhaoyilun
2026-07-10 09:52:34 +08:00
parent ea38346ce3
commit 5578f0bda7
6 changed files with 687 additions and 3 deletions

View File

@@ -0,0 +1,43 @@
param()
$ErrorActionPreference = "Stop"
Set-StrictMode -Version Latest
$repo = (Resolve-Path -LiteralPath (Join-Path $PSScriptRoot "..")).Path
$script = Join-Path $repo "scripts\verify-file-cache-mapping.ps1"
$tempDir = Join-Path $repo ("runs\file-cache-mapping-test-" + [guid]::NewGuid().ToString("N"))
$archiveList = Join-Path $tempDir "archive-list.txt"
function Assert-True([bool]$Condition, [string]$Message) {
if (-not $Condition) { throw $Message }
}
try {
New-Item -ItemType Directory -Force -Path $tempDir | Out-Null
@(
"C:\redacted\importal\aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\redacted-report.docx",
"C:\redacted\importal\bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb\redacted-sheet.xlsx",
"C:\redacted\other\ignored.txt"
) | Set-Content -LiteralPath $archiveList -Encoding UTF8
$output = & powershell -NoProfile -ExecutionPolicy Bypass -File $script -ArchiveListPath $archiveList -SkipDb
if ($LASTEXITCODE -ne 0) {
throw "verify-file-cache-mapping.ps1 failed with exit code $LASTEXITCODE"
}
$json = $output | ConvertFrom-Json
Assert-True ($json.ok -eq $true) "ok should be true"
Assert-True ($json.cache_checked -eq $true) "cache should be checked"
Assert-True ($json.cache_candidate_count -eq 2) "cache candidate count should be 2"
Assert-True ($json.cache_extension_counts.".docx" -eq 1) "docx extension count should be 1"
Assert-True ($json.cache_extension_counts.".xlsx" -eq 1) "xlsx extension count should be 1"
Assert-True ($json.hash_dir_length_counts."32" -eq 2) "hash dir length count should be 2"
Assert-True ($json.raw_paths_printed -eq $false) "raw paths must not be printed"
Assert-True ($json.file_contents_read -eq $false) "file contents must not be read"
Assert-True ($json.file_paths_returned -eq $false) "file paths must not be returned"
}
finally {
if (Test-Path -LiteralPath $tempDir) {
Remove-Item -LiteralPath $tempDir -Recurse -Force
}
}

View File

@@ -0,0 +1,552 @@
param(
[string]$ArchiveListPath = "",
[string]$CacheRoot = "",
[string]$SQLiteDllPath = $env:ISPHERE_MSGLIB_SQLITE_DLL,
[string]$DbPath = $env:ISPHERE_MSGLIB_DB,
[string]$Password = "123",
[switch]$SkipDb
)
$ErrorActionPreference = "Stop"
Set-StrictMode -Version Latest
$repo = (Resolve-Path -LiteralPath (Join-Path $PSScriptRoot "..")).Path
function Add-Count([hashtable]$Map, [string]$Key, [int]$Increment = 1) {
if ([string]::IsNullOrWhiteSpace($Key)) { return }
if ($Map.ContainsKey($Key)) {
$Map[$Key] = [int]$Map[$Key] + $Increment
}
else {
$Map[$Key] = $Increment
}
}
function Get-Sha256Text([string]$Value) {
$sha = [System.Security.Cryptography.SHA256]::Create()
try {
$bytes = [System.Text.Encoding]::UTF8.GetBytes($Value)
$hash = $sha.ComputeHash($bytes)
return (($hash | ForEach-Object { $_.ToString("x2") }) -join "")
}
finally {
$sha.Dispose()
}
}
function Normalize-FileName([string]$Value) {
if ([string]::IsNullOrWhiteSpace($Value)) { return "" }
$leaf = ($Value -split '[\\/]')[-1]
return $leaf.Trim().ToLowerInvariant()
}
function Normalize-Extension([string]$Value) {
if ([string]::IsNullOrWhiteSpace($Value)) { return "" }
$extension = $Value.Trim().ToLowerInvariant()
if ($extension -match '^\.[a-z0-9]{1,8}$') { return $extension }
return ".other"
}
function New-EmptyCacheSummary {
return [ordered]@{
checked = $false
candidate_count = 0
extension_counts = @{}
hash_dir_length_counts = @{}
hash_dir_value_hash_counts = @{}
filename_hash_counts = @{}
filename_size_hash_counts = @{}
has_size_data = $false
}
}
function Add-CacheCandidate($Summary, [string]$Name, [Nullable[Int64]]$Size, [string]$HashDir) {
$normalizedName = Normalize-FileName $Name
if ($normalizedName -eq "") { return }
$extension = Normalize-Extension ([System.IO.Path]::GetExtension($normalizedName))
if ($extension -ne "") {
Add-Count $Summary.extension_counts $extension
}
if (-not [string]::IsNullOrWhiteSpace($HashDir)) {
Add-Count $Summary.hash_dir_length_counts ([string]$HashDir.Length)
Add-Count $Summary.hash_dir_value_hash_counts (Get-Sha256Text $HashDir.ToLowerInvariant())
}
Add-Count $Summary.filename_hash_counts (Get-Sha256Text $normalizedName)
if ($null -ne $Size -and $Size.Value -ge 0) {
$Summary["has_size_data"] = $true
Add-Count $Summary.filename_size_hash_counts (Get-Sha256Text ($normalizedName + "|" + $Size.Value))
}
$Summary["candidate_count"] = [int]$Summary["candidate_count"] + 1
}
function Get-HashDirFromPathText([string]$Value) {
$match = [regex]::Match($Value, '(?i)(?:^|[\\/])importal[\\/]([0-9a-f]{32,})(?:[\\/])')
if ($match.Success) {
return $match.Groups[1].Value.ToLowerInvariant()
}
return ""
}
function Read-CacheSummaryFromArchiveList([string]$Path) {
if (-not (Test-Path -LiteralPath $Path)) {
throw "ArchiveListPath not found"
}
$summary = New-EmptyCacheSummary
$summary["checked"] = $true
foreach ($line in Get-Content -LiteralPath $Path) {
$text = [string]$line
$hashDir = Get-HashDirFromPathText $text
if ($hashDir -eq "") { continue }
Add-CacheCandidate $summary $text $null $hashDir
}
return $summary
}
function Read-CacheSummaryFromRoot([string]$Path) {
if (-not (Test-Path -LiteralPath $Path)) {
throw "CacheRoot not found"
}
$summary = New-EmptyCacheSummary
$summary["checked"] = $true
foreach ($file in Get-ChildItem -LiteralPath $Path -File -Recurse) {
$hashDir = Get-HashDirFromPathText $file.FullName
if ($hashDir -eq "") { continue }
Add-CacheCandidate $summary $file.Name ([Int64]$file.Length) $hashDir
}
return $summary
}
function Convert-CountObjectToHashtable($Value) {
$map = @{}
if ($null -eq $Value) { return $map }
if ($Value -is [System.Collections.IDictionary]) {
foreach ($key in $Value.Keys) {
$map[[string]$key] = [int]$Value[$key]
}
return $map
}
foreach ($property in $Value.PSObject.Properties) {
$map[$property.Name] = [int]$property.Value
}
return $map
}
function Count-Intersections([hashtable]$Left, [hashtable]$Right) {
$count = 0
foreach ($key in $Left.Keys) {
if ($Right.ContainsKey($key)) {
$count += [Math]::Min([int]$Left[$key], [int]$Right[$key])
}
}
return $count
}
function Count-UniqueIntersections([hashtable]$Left, [hashtable]$Right) {
$count = 0
foreach ($key in $Left.Keys) {
if ($Right.ContainsKey($key) -and [int]$Left[$key] -eq 1 -and [int]$Right[$key] -eq 1) {
$count++
}
}
return $count
}
function Invoke-ReceiveFileRecordProbe([string]$SQLiteDll, [string]$Database, [string]$DbPassword) {
if (-not (Test-Path -LiteralPath $SQLiteDll)) {
throw "SQLite DLL not found"
}
if (-not (Test-Path -LiteralPath $Database)) {
throw "MsgLib DB not found"
}
$tempDir = Join-Path $repo ("runs\file-cache-mapping-db-probe-" + [guid]::NewGuid().ToString("N"))
$source = Join-Path $tempDir "ReceiveFileRecordProbe.cs"
$exe = Join-Path $tempDir "ReceiveFileRecordProbe.exe"
$sqliteCopy = Join-Path $tempDir "System.Data.SQLite.dll"
$csc = "$env:WINDIR\Microsoft.NET\Framework\v4.0.30319\csc.exe"
if (-not (Test-Path -LiteralPath $csc)) {
throw "32-bit .NET Framework csc.exe v4.0.30319 not found"
}
try {
New-Item -ItemType Directory -Force -Path $tempDir | Out-Null
Copy-Item -LiteralPath $SQLiteDll -Destination $sqliteCopy -Force
@'
using System;
using System.Collections.Generic;
using System.Data.Common;
using System.IO;
using System.Reflection;
using System.Security.Cryptography;
using System.Text;
using System.Web.Script.Serialization;
internal static class ReceiveFileRecordProbe
{
private static int Main(string[] args)
{
try
{
string sqliteDllPath = args[0];
string dbPath = args[1];
string password = args.Length > 2 ? args[2] : "123";
AppDomain.CurrentDomain.AssemblyResolve += delegate(object sender, ResolveEventArgs eventArgs)
{
if (eventArgs.Name.StartsWith("System.Data.SQLite", StringComparison.OrdinalIgnoreCase))
{
return Assembly.LoadFrom(sqliteDllPath);
}
return null;
};
Assembly sqliteAssembly = Assembly.LoadFrom(sqliteDllPath);
Type factoryType = sqliteAssembly.GetType("System.Data.SQLite.SQLiteFactory", true);
FieldInfo instanceField = factoryType.GetField("Instance", BindingFlags.Public | BindingFlags.Static);
DbProviderFactory factory = (DbProviderFactory)instanceField.GetValue(null);
var result = NewResult();
using (DbConnection connection = factory.CreateConnection())
{
connection.ConnectionString = "Data Source=" + dbPath + ";Version=3;Read Only=True;Password=" + password + ";";
connection.Open();
ExecuteNonQuery(connection, "PRAGMA query_only=ON");
if (!TableExists(connection, "TD_ReceiveFileRecord"))
{
PrintJson(result);
return 0;
}
result["table_available"] = true;
HashSet<string> columns = ReadColumns(connection, "TD_ReceiveFileRecord");
string msgColumn = ExistingColumn(columns, "ReceiveMsgGuid");
string nameColumn = ExistingColumn(columns, "FileName");
string sizeColumn = ExistingColumn(columns, "FileSize", "Size");
string sourceColumn = ExistingColumn(columns, "SourceID", "FileGuid", "FileId");
if (nameColumn == "")
{
PrintJson(result);
return 0;
}
string sql = "select " +
SelectColumn(msgColumn, "receive_msg_guid") + ", " +
SelectColumn(nameColumn, "file_name") + ", " +
SelectColumn(sizeColumn, "size_bytes") + ", " +
SelectColumn(sourceColumn, "source_id") +
" from " + QuoteIdent("TD_ReceiveFileRecord") + " limit 100000";
using (DbCommand command = connection.CreateCommand())
{
command.CommandText = sql;
using (DbDataReader reader = command.ExecuteReader())
{
while (reader.Read())
{
result["record_count"] = (int)result["record_count"] + 1;
string receiveMsgGuid = ReaderString(reader, "receive_msg_guid");
string fileName = SafeFileName(ReaderString(reader, "file_name"));
long size = ReaderInt64(reader, "size_bytes");
string sourceId = ReaderString(reader, "source_id").Trim().ToLowerInvariant();
if (receiveMsgGuid.Trim() != "") result["receive_msg_guid_present_count"] = (int)result["receive_msg_guid_present_count"] + 1;
if (fileName.Trim() != "") result["filename_present_count"] = (int)result["filename_present_count"] + 1;
if (size > 0) result["size_present_count"] = (int)result["size_present_count"] + 1;
if (sourceId != "") result["source_id_present_count"] = (int)result["source_id_present_count"] + 1;
string normalizedName = fileName.Trim().ToLowerInvariant();
if (normalizedName != "")
{
AddCount((Dictionary<string, object>)result["extension_counts"], SafeExtension(Path.GetExtension(normalizedName)));
AddCount((Dictionary<string, object>)result["filename_hash_counts"], Sha256(normalizedName));
if (size > 0) AddCount((Dictionary<string, object>)result["filename_size_hash_counts"], Sha256(normalizedName + "|" + size.ToString()));
}
if (sourceId != "")
{
AddCount((Dictionary<string, object>)result["source_id_hash_counts"], Sha256(sourceId));
if (IsHexLike(sourceId)) result["source_id_hash_shape_count"] = (int)result["source_id_hash_shape_count"] + 1;
}
}
}
}
}
PrintJson(result);
return 0;
}
catch (Exception ex)
{
Console.Error.WriteLine(ex.GetType().Name + ": " + ex.Message);
return 1;
}
}
private static Dictionary<string, object> NewResult()
{
return new Dictionary<string, object>
{
{ "table_available", false },
{ "record_count", 0 },
{ "filename_present_count", 0 },
{ "size_present_count", 0 },
{ "source_id_present_count", 0 },
{ "receive_msg_guid_present_count", 0 },
{ "source_id_hash_shape_count", 0 },
{ "extension_counts", new Dictionary<string, object>() },
{ "filename_hash_counts", new Dictionary<string, object>() },
{ "filename_size_hash_counts", new Dictionary<string, object>() },
{ "source_id_hash_counts", new Dictionary<string, object>() }
};
}
private static void PrintJson(Dictionary<string, object> value)
{
Console.WriteLine(new JavaScriptSerializer().Serialize(value));
}
private static void AddCount(Dictionary<string, object> map, string key)
{
if (string.IsNullOrWhiteSpace(key)) return;
if (map.ContainsKey(key)) map[key] = (int)map[key] + 1;
else map[key] = 1;
}
private static bool TableExists(DbConnection connection, string table)
{
using (DbCommand command = connection.CreateCommand())
{
command.CommandText = "select count(*) from sqlite_master where type='table' and name=@name";
DbParameter parameter = command.CreateParameter();
parameter.ParameterName = "@name";
parameter.Value = table;
command.Parameters.Add(parameter);
return Convert.ToInt32(command.ExecuteScalar()) > 0;
}
}
private static HashSet<string> ReadColumns(DbConnection connection, string table)
{
var columns = new HashSet<string>(StringComparer.OrdinalIgnoreCase);
using (DbCommand command = connection.CreateCommand())
{
command.CommandText = "pragma table_info(" + QuoteIdent(table) + ")";
using (DbDataReader reader = command.ExecuteReader())
{
while (reader.Read()) columns.Add(Convert.ToString(reader["name"]));
}
}
return columns;
}
private static string ExistingColumn(HashSet<string> columns, params string[] names)
{
foreach (string name in names)
{
if (!string.IsNullOrWhiteSpace(name) && columns.Contains(name)) return name;
}
return "";
}
private static string SelectColumn(string column, string alias)
{
if (string.IsNullOrWhiteSpace(column)) return "'' as " + QuoteIdent(alias);
return QuoteIdent(column) + " as " + QuoteIdent(alias);
}
private static string QuoteIdent(string value)
{
return "\"" + value.Replace("\"", "\"\"") + "\"";
}
private static string ReaderString(DbDataReader reader, string column)
{
object value = reader[column];
if (value == null || value == DBNull.Value) return "";
return Convert.ToString(value);
}
private static long ReaderInt64(DbDataReader reader, string column)
{
object value = reader[column];
if (value == null || value == DBNull.Value) return 0;
long parsed;
if (long.TryParse(Convert.ToString(value), out parsed)) return parsed;
return 0;
}
private static string SafeFileName(string value)
{
if (string.IsNullOrWhiteSpace(value)) return "";
try { return Path.GetFileName(value); }
catch
{
int slash = Math.Max(value.LastIndexOf('/'), value.LastIndexOf('\\'));
if (slash >= 0 && slash + 1 < value.Length) return value.Substring(slash + 1);
return value;
}
}
private static string SafeExtension(string value)
{
if (string.IsNullOrWhiteSpace(value)) return "";
string extension = value.Trim().ToLowerInvariant();
if (extension.Length < 2 || extension.Length > 9) return ".other";
if (extension[0] != '.') return ".other";
for (int i = 1; i < extension.Length; i++)
{
char c = extension[i];
bool ok = (c >= 'a' && c <= 'z') || (c >= '0' && c <= '9');
if (!ok) return ".other";
}
return extension;
}
private static bool IsHexLike(string value)
{
if (value.Length < 16) return false;
foreach (char c in value)
{
bool ok = (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F');
if (!ok) return false;
}
return true;
}
private static string Sha256(string value)
{
using (SHA256 sha = SHA256.Create())
{
byte[] hash = sha.ComputeHash(Encoding.UTF8.GetBytes(value));
var builder = new StringBuilder(hash.Length * 2);
foreach (byte b in hash) builder.Append(b.ToString("x2"));
return builder.ToString();
}
}
private static void ExecuteNonQuery(DbConnection connection, string sql)
{
using (DbCommand command = connection.CreateCommand())
{
command.CommandText = sql;
command.ExecuteNonQuery();
}
}
}
'@ | Set-Content -LiteralPath $source -Encoding UTF8
& $csc `
/nologo `
/target:exe `
/platform:x86 `
/optimize+ `
/warn:0 `
/out:$exe `
/reference:System.dll `
/reference:System.Core.dll `
/reference:System.Data.dll `
/reference:System.Web.Extensions.dll `
/reference:$sqliteCopy `
$source | Out-Null
if ($LASTEXITCODE -ne 0) {
throw "ReceiveFileRecordProbe compilation failed"
}
@'
<?xml version="1.0" encoding="utf-8" ?>
<configuration>
<startup useLegacyV2RuntimeActivationPolicy="true">
<supportedRuntime version="v4.0" />
<supportedRuntime version="v2.0.50727" />
</startup>
</configuration>
'@ | Set-Content -LiteralPath ($exe + ".config") -Encoding UTF8
$output = & $exe $sqliteCopy $Database $DbPassword
if ($LASTEXITCODE -ne 0) {
throw "ReceiveFileRecordProbe failed"
}
return $output | ConvertFrom-Json
}
finally {
if (Test-Path -LiteralPath $tempDir) {
Remove-Item -LiteralPath $tempDir -Recurse -Force
}
}
}
$cacheSummary = New-EmptyCacheSummary
if (-not [string]::IsNullOrWhiteSpace($ArchiveListPath)) {
$cacheSummary = Read-CacheSummaryFromArchiveList $ArchiveListPath
}
elseif (-not [string]::IsNullOrWhiteSpace($CacheRoot)) {
$cacheSummary = Read-CacheSummaryFromRoot $CacheRoot
}
$dbChecked = $false
$dbProbe = [ordered]@{
table_available = $false
record_count = 0
filename_present_count = 0
size_present_count = 0
source_id_present_count = 0
receive_msg_guid_present_count = 0
source_id_hash_shape_count = 0
extension_counts = @{}
filename_hash_counts = @{}
filename_size_hash_counts = @{}
source_id_hash_counts = @{}
}
if (-not $SkipDb) {
if ([string]::IsNullOrWhiteSpace($SQLiteDllPath) -or [string]::IsNullOrWhiteSpace($DbPath)) {
throw "MsgLib DB probe requires SQLiteDllPath and DbPath, or pass -SkipDb"
}
$dbProbe = Invoke-ReceiveFileRecordProbe $SQLiteDllPath $DbPath $Password
$dbChecked = $true
}
$dbFilenameHashes = Convert-CountObjectToHashtable $dbProbe.filename_hash_counts
$dbFilenameSizeHashes = Convert-CountObjectToHashtable $dbProbe.filename_size_hash_counts
$dbSourceIDHashes = Convert-CountObjectToHashtable $dbProbe.source_id_hash_counts
$cacheFilenameHashes = [hashtable]$cacheSummary["filename_hash_counts"]
$cacheFilenameSizeHashes = [hashtable]$cacheSummary["filename_size_hash_counts"]
$cacheHashDirValueHashes = [hashtable]$cacheSummary["hash_dir_value_hash_counts"]
$filenameOnlyMatches = Count-Intersections $dbFilenameHashes $cacheFilenameHashes
$filenameSizeMatches = Count-Intersections $dbFilenameSizeHashes $cacheFilenameSizeHashes
$uniqueFilenameSizeMatches = Count-UniqueIntersections $dbFilenameSizeHashes $cacheFilenameSizeHashes
$sourceIDHashDirMatches = Count-Intersections $dbSourceIDHashes $cacheHashDirValueHashes
$mappingValidated = ($uniqueFilenameSizeMatches -gt 0 -and [bool]$cacheSummary["has_size_data"])
$recommendedNextNode = "additional evidence request"
if ($mappingValidated) {
$recommendedNextNode = "R4 cache-file resolver candidate"
}
elseif ($filenameOnlyMatches -gt 0 -or $sourceIDHashDirMatches -gt 0) {
$recommendedNextNode = "additional evidence request: collect file size or cache root metadata"
}
[ordered]@{
ok = $true
verification = "file_cache_mapping"
db_checked = $dbChecked
db_table_available = [bool]$dbProbe.table_available
db_record_count = [int]$dbProbe.record_count
db_filename_present_count = [int]$dbProbe.filename_present_count
db_size_present_count = [int]$dbProbe.size_present_count
db_source_id_present_count = [int]$dbProbe.source_id_present_count
db_receive_msg_guid_present_count = [int]$dbProbe.receive_msg_guid_present_count
db_source_id_hash_shape_count = [int]$dbProbe.source_id_hash_shape_count
db_extension_counts = $dbProbe.extension_counts
cache_checked = [bool]$cacheSummary["checked"]
cache_candidate_count = [int]$cacheSummary["candidate_count"]
cache_extension_counts = $cacheSummary["extension_counts"]
hash_dir_length_counts = $cacheSummary["hash_dir_length_counts"]
filename_only_match_count = $filenameOnlyMatches
filename_size_match_count = $filenameSizeMatches
unique_filename_size_match_count = $uniqueFilenameSizeMatches
source_id_hash_dir_match_count = $sourceIDHashDirMatches
mapping_validated = $mappingValidated
recommended_next_node = $recommendedNextNode
raw_paths_printed = $false
file_contents_read = $false
file_paths_returned = $false
raw_rows_returned = $false
message_body_values_printed = $false
} | ConvertTo-Json -Depth 8 -Compress