Files
URLNotesGrabberCore/URLNotesGrabberCORE/UpdateBlogPathsRunner.cs
jimandClaude Opus 5 8f4177a0c9 feat: fold the TTFolderPath refresh into --output
TL.db syncs between machines whose absolute paths differ, so a single
TTFolderPath column cannot be correct on both at once -- the stored paths are
only trustworthy on the machine that wrote them. That made --updatepaths a
mandatory prelude to every --output rather than the one-time setup step it
looks like.

--output now refreshes the column from the TumblThree Index metadata before
exporting. The root comes from the first non-flag argument, else
appSettings:PathTTRoot. With no root available it says so and exports whatever
TL.db already holds; a root whose Index folder is missing is a hard stop, since
silently exporting stale paths is the failure this change exists to prevent.
--norefresh skips the refresh for a pure export.

The scan is extracted from UpdateBlogPathsRunner.Run into a reusable Scan() that
returns counts instead of only printing them, so --updatepaths keeps its
per-file detail while --output prints a single summary line rather than a few
hundred lines ahead of the export.

Verified against a throwaway database: a stale cross-machine path is repaired
and the export lands in the correct local folder; no configured root warns and
continues (exit 0); a missing Index folder stops (exit 1); --norefresh skips the
refresh and exports (exit 0).

Co-Authored-By: Claude Opus 5 <[email protected]>
2026-08-05 12:09:55 -05:00

165 lines
6.5 KiB
C#

using System.Text.Json;
namespace URLNotesGrabberCORE
{
// Port of ThreeTxtFileHelper/UpdateBlogPaths.cs. Reads .tumblr / .tmblrpriv metadata
// files from a root\Index folder and populates Blogs.TTFolderPath in TL.db.
//
// Scan() is the reusable engine: --updatepaths wraps it as a standalone command and
// --output calls it as a refresh step, because a TL.db synced between machines cannot
// hold one absolute path that is correct on both.
public static class UpdateBlogPathsRunner
{
public enum ScanOutcome
{
Completed,
NoRootConfigured,
IndexFolderMissing
}
public sealed class ScanResult
{
public ScanOutcome Outcome { get; init; }
public string RootPath { get; init; } = string.Empty;
public string IndexPath { get; init; } = string.Empty;
public int MetadataFiles { get; init; }
public int Written { get; init; }
public int Unchanged { get; init; }
public int NoLocation { get; init; }
public int NoMatchingRow { get; init; }
public int Errors { get; init; }
}
// verbose: log a line per metadata file. --updatepaths wants that detail; --output
// only wants the counts, since a few hundred lines before the export would bury it.
public static ScanResult Scan(string? rootPath, bool verbose)
{
if (string.IsNullOrWhiteSpace(rootPath))
return new ScanResult { Outcome = ScanOutcome.NoRootConfigured };
DataAccess.EnsureTTFileHelperColumnsExist();
string indexPath = Path.Combine(rootPath, "Index");
if (!Directory.Exists(indexPath))
{
return new ScanResult
{
Outcome = ScanOutcome.IndexFolderMissing,
RootPath = rootPath,
IndexPath = indexPath
};
}
var blogFiles = Directory.GetFiles(indexPath, "*.tumblr")
.Concat(Directory.GetFiles(indexPath, "*.tmblrpriv"))
.ToList();
if (verbose)
Console.WriteLine($"Found {blogFiles.Count} blog metadata files");
int updatedCount = 0;
int unchangedCount = 0;
int noLocationCount = 0;
int noRowCount = 0;
int errorCount = 0;
foreach (var blogFile in blogFiles)
{
try
{
string blogName = Path.GetFileNameWithoutExtension(blogFile);
string jsonContent = File.ReadAllText(blogFile);
using JsonDocument doc = JsonDocument.Parse(jsonContent);
JsonElement root = doc.RootElement;
if (root.TryGetProperty("FileDownloadLocation", out JsonElement locationElement))
{
string? fileDownloadLocation = locationElement.GetString()?.Trim();
if (!string.IsNullOrWhiteSpace(fileDownloadLocation))
{
// Report the database's answer, not the fact that the file parsed.
if (DataAccess.SetBlogTTFolderPath(blogName, fileDownloadLocation))
{
updatedCount++;
if (verbose)
Console.WriteLine($"Updated {blogName}: {fileDownloadLocation}");
}
else if (DataAccess.BlogExists(blogName))
{
unchangedCount++;
}
else
{
noRowCount++;
Console.WriteLine($"No Blogs row named '{blogName}' -- path not stored (name may differ in case)");
}
}
else
{
noLocationCount++;
if (verbose)
Console.WriteLine($"Empty FileDownloadLocation in {blogFile}");
}
}
else
{
noLocationCount++;
if (verbose)
Console.WriteLine($"No FileDownloadLocation found in {blogFile}");
}
}
catch (Exception ex)
{
errorCount++;
Console.WriteLine($"Error processing {blogFile}: {ex.Message}");
}
}
return new ScanResult
{
Outcome = ScanOutcome.Completed,
RootPath = rootPath,
IndexPath = indexPath,
MetadataFiles = blogFiles.Count,
Written = updatedCount,
Unchanged = unchangedCount,
NoLocation = noLocationCount,
NoMatchingRow = noRowCount,
Errors = errorCount
};
}
public static int Run(string rootPath)
{
if (string.IsNullOrWhiteSpace(rootPath))
{
Console.WriteLine("UpdateBlogPaths: rootPath is required.");
return 1;
}
string indexPath = Path.Combine(rootPath, "Index");
Console.WriteLine($"Scanning Index folder: {indexPath}");
var result = Scan(rootPath, verbose: true);
if (result.Outcome == ScanOutcome.IndexFolderMissing)
{
Console.WriteLine($"Index folder not found at: {result.IndexPath}");
return 1;
}
Console.WriteLine($"\n========== UpdateBlogPaths summary ==========");
Console.WriteLine($"Metadata files: {result.MetadataFiles}");
Console.WriteLine($"TTFolderPath written: {result.Written}");
Console.WriteLine($"Already correct: {result.Unchanged}");
Console.WriteLine($"No FileDownloadLocation: {result.NoLocation}");
Console.WriteLine($"No matching blog row: {result.NoMatchingRow}");
Console.WriteLine($"Errors: {result.Errors}");
Console.WriteLine($"\nBlogs now holding a TTFolderPath: {DataAccess.CountBlogsWithTTFolderPath()}");
return result.Errors == 0 ? 0 : 2;
}
}
}