4 Commits
Author SHA1 Message Date
jim 70b32dfc89 Merge branch 'claude/ttfolderpath-not-set-8c9b45' into master 2026-08-05 12:09:55 -05:00
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
jim a2763d0026 Merge branch 'claude/ttfolderpath-not-set-8c9b45' into master 2026-08-05 12:02:58 -05:00
jimandClaude Opus 5 721224bc13 fix: make --output and --updatepaths tell the truth about TTFolderPath
--output iterated all 156k active Blogs rows and printed a "does not exist or is
not set" skip line for each, which is nearly every blog in the crawl registry --
only the few hundred downloaded locally ever have a folder. The signal was
buried in six figures of noise.

GetAllBlogsWithTTFolderPath now selects only active blogs carrying a non-empty
path, so --output processes export targets and nothing else. When none exist it
says so once, names the database it read, points at --updatepaths, and returns
non-zero instead of reporting success. A stored path this machine cannot see is
now reported separately from an unset one, with the path shown, because the two
are fixed in different places. Paths are trimmed before Directory.Exists, which
stray whitespace in a .tumblr FileDownloadLocation would otherwise defeat.

Both writers counted optimistically. UpdateBlogPathsRunner printed its
per-blog success line and incremented its total from the metadata file parsing,
never checking whether the UPDATE matched a row; LegacyPostsDbImporter counted a
blog as copied even when the legacy TTFolderPath was NULL. Either could report
full success having written nothing -- which is consistent with TL.db holding
zero populated paths across all 156,492 active blogs despite 20,679 posts having
merged. SetBlogTTFolderPath now returns whether a row changed, and both callers
report written / already-correct / no-matching-row separately.

Verified against a throwaway database: no-paths case, export case (stale .txt
rotated to .bak, per-PostType files, date-sorted), missing-folder case,
--updatepaths honest counts, and an idempotent rerun reporting already-correct.

Co-Authored-By: Claude Opus 5 <[email protected]>
2026-08-05 12:02:49 -05:00
5 changed files with 264 additions and 43 deletions
+56 -10
View File
@@ -106,6 +106,10 @@ namespace URLNotesGrabberCORE
}
}
// The database every DataAccess call defaults to, exposed so modes can report
// which file they actually read when their results are surprising.
public static string GetActiveDbPath() => GetDefaultDbPath();
private static string GetDefaultDbPath()
{
if (_cachedDbPath != null)
@@ -2304,7 +2308,11 @@ namespace URLNotesGrabberCORE
};
}
public static void SetBlogTTFolderPath(string blogName, string? path, string? DBPath = null)
// Returns true only when a row's TTFolderPath actually changed. A false means either
// the row already held this value or no row matched the name -- callers must not
// report a write they did not get, which is how a --updatepaths run could once print
// "Updated <blog>" for every metadata file while leaving the column entirely NULL.
public static bool SetBlogTTFolderPath(string blogName, string? path, string? DBPath = null)
{
DBPath ??= GetDefaultDbPath();
try { AddBlog(blogName, false, DBPath); } catch { }
@@ -2317,7 +2325,21 @@ namespace URLNotesGrabberCORE
cmd.Parameters.AddWithValue("@path", (object?)path ?? DBNull.Value);
cmd.Parameters.AddWithValue("@modified", DateTime.Now.ToString("yyyy-MM-dd HH:mm:ss"));
cmd.Parameters.AddWithValue("@name", blogName);
cmd.ExecuteNonQuery();
return cmd.ExecuteNonQuery() > 0;
}
// Whether a Blogs row exists under this exact name. BlogName is a BINARY-collated
// primary key, so a metadata filename that differs only in case is a different blog
// as far as the UPDATE above is concerned -- worth telling the user about.
public static bool BlogExists(string blogName, string? DBPath = null)
{
DBPath ??= GetDefaultDbPath();
using var connection = new SQLiteConnection("Data Source=" + DBPath);
connection.Open();
using var cmd = new SQLiteCommand("SELECT 1 FROM Blogs WHERE BlogName = @name", connection);
cmd.Parameters.AddWithValue("@name", blogName);
return cmd.ExecuteScalar() != null;
}
// Partial UPDATE used by the correct-apply path. fieldsToUpdate maps
@@ -2391,24 +2413,48 @@ namespace URLNotesGrabberCORE
};
}
public static List<(string BlogName, string? TTFolderPath)> GetAllBlogsWithTTFolderPath(string? DBPath = null)
// Export targets only: active blogs that actually carry a TTFolderPath.
// Blogs is a 144k-row crawl registry and only the few hundred blogs downloaded
// locally have a folder, so returning the unset rows made --output print a skip
// line for every blog Tumblr has ever handed us.
public static List<(string BlogName, string TTFolderPath)> GetAllBlogsWithTTFolderPath(string? DBPath = null)
{
DBPath ??= GetDefaultDbPath();
var results = new List<(string, string?)>();
var results = new List<(string, string)>();
using var connection = new SQLiteConnection("Data Source=" + DBPath);
connection.Open();
using var cmd = new SQLiteCommand("SELECT BlogName, TTFolderPath FROM Blogs WHERE IsActive = 1", connection);
using var cmd = new SQLiteCommand(
"SELECT BlogName, TRIM(TTFolderPath) FROM Blogs WHERE IsActive = 1 AND IFNULL(TRIM(TTFolderPath), '') <> '' ORDER BY BlogName",
connection);
using var reader = cmd.ExecuteReader();
while (reader.Read())
{
string name = reader.GetString(0);
string? path = reader.IsDBNull(1) ? null : reader.GetString(1);
results.Add((name, path));
}
results.Add((reader.GetString(0), reader.GetString(1)));
return results;
}
// Companion counts for the messages --output and --updatepaths print about coverage.
public static int CountActiveBlogs(string? DBPath = null)
{
DBPath ??= GetDefaultDbPath();
using var connection = new SQLiteConnection("Data Source=" + DBPath);
connection.Open();
using var cmd = new SQLiteCommand("SELECT COUNT(*) FROM Blogs WHERE IsActive = 1", connection);
return Convert.ToInt32(cmd.ExecuteScalar());
}
public static int CountBlogsWithTTFolderPath(string? DBPath = null)
{
DBPath ??= GetDefaultDbPath();
using var connection = new SQLiteConnection("Data Source=" + DBPath);
connection.Open();
using var cmd = new SQLiteCommand(
"SELECT COUNT(*) FROM Blogs WHERE IFNULL(TRIM(TTFolderPath), '') <> ''", connection);
return Convert.ToInt32(cmd.ExecuteScalar());
}
private static string SafeStr(SQLiteDataReader reader, int ordinal)
{
return reader.IsDBNull(ordinal) ? string.Empty : reader.GetValue(ordinal)?.ToString() ?? string.Empty;
+12 -3
View File
@@ -29,6 +29,8 @@ namespace URLNotesGrabberCORE
Console.WriteLine($"Reading legacy posts.db: {legacyDbPath}");
int blogsCopied = 0;
int blogPathsWritten = 0;
int blogsWithoutPath = 0;
int postsUpserted = 0;
int errors = 0;
@@ -48,7 +50,13 @@ namespace URLNotesGrabberCORE
if (string.IsNullOrWhiteSpace(blogName)) continue;
try
{
DataAccess.SetBlogTTFolderPath(blogName, ttFolderPath);
// A legacy row whose TTFolderPath was already NULL copies nothing.
// Counting it as "copied" is what hid the fact that this import has
// never populated a single path.
if (string.IsNullOrWhiteSpace(ttFolderPath))
blogsWithoutPath++;
else if (DataAccess.SetBlogTTFolderPath(blogName, ttFolderPath.Trim()))
blogPathsWritten++;
blogsCopied++;
}
catch (Exception ex)
@@ -58,7 +66,7 @@ namespace URLNotesGrabberCORE
}
}
}
Console.WriteLine($" Blogs copied: {blogsCopied}");
Console.WriteLine($" Blogs seen: {blogsCopied}, TTFolderPath written: {blogPathsWritten}, legacy rows with no path: {blogsWithoutPath}");
// 2) Copy Posts
try
@@ -138,7 +146,8 @@ namespace URLNotesGrabberCORE
}
Console.WriteLine($"\n========== Legacy import summary ==========");
Console.WriteLine($"Blogs copied: {blogsCopied}");
Console.WriteLine($"Blogs seen: {blogsCopied}");
Console.WriteLine($"Paths written: {blogPathsWritten} (legacy rows with no path: {blogsWithoutPath})");
Console.WriteLine($"Posts upserted: {postsUpserted}");
Console.WriteLine($"Errors: {errors}");
return errors == 0 ? 0 : 2;
+81 -11
View File
@@ -8,28 +8,51 @@ namespace URLNotesGrabberCORE
// field order). Reads from TL.db via DataAccess.GetAllPostsForBlog.
public static class OutputMode
{
public static int Run(IConfiguration config)
public static int Run(IConfiguration config, string[]? args = null)
{
DataAccess.EnsureTTFileHelperColumnsExist();
var blogs = DataAccess.GetAllBlogsWithTTFolderPath();
Console.WriteLine($"Found {blogs.Count} blog(s) to process.");
string dbPath = DataAccess.GetActiveDbPath();
Console.WriteLine($"Database: {Path.GetFullPath(dbPath)}");
foreach (var (blogName, ttFolderPath) in blogs)
if (!RefreshPaths(config, args ?? Array.Empty<string>()))
return 1;
var blogs = DataAccess.GetAllBlogsWithTTFolderPath();
int activeBlogs = DataAccess.CountActiveBlogs();
Console.WriteLine($"{blogs.Count} of {activeBlogs} active blog(s) have a TTFolderPath.");
if (blogs.Count == 0)
{
Console.WriteLine($"\nNothing to export: no blog in {Path.GetFullPath(dbPath)} has a TTFolderPath.");
Console.WriteLine("Point --output at a TumblThree root so it can populate them: --output <root>,");
Console.WriteLine("or set appSettings:PathTTRoot so the refresh runs automatically.");
return 1;
}
int missingFolderCount = 0;
int writtenCount = 0;
foreach (var (blogName, folder) in blogs)
{
Console.WriteLine($"\nProcessing blog: {blogName}");
if (string.IsNullOrWhiteSpace(ttFolderPath) || !Directory.Exists(ttFolderPath))
// A stored path that this machine cannot see means the value was written on
// another machine -- re-running --updatepaths locally is the fix, so say so
// rather than lumping it in with "not set".
if (!Directory.Exists(folder))
{
Console.WriteLine($" TTFolderPath does not exist or is not set. Skipping.");
Console.WriteLine($" TTFolderPath folder not found: {folder}. Skipping.");
missingFolderCount++;
continue;
}
Console.WriteLine($" TTFolderPath: {ttFolderPath}");
Console.WriteLine($" TTFolderPath: {folder}");
writtenCount++;
try
{
foreach (var bakFile in Directory.GetFiles(ttFolderPath, "*.bak"))
foreach (var bakFile in Directory.GetFiles(folder, "*.bak"))
File.Delete(bakFile);
}
catch (Exception ex)
@@ -37,7 +60,7 @@ namespace URLNotesGrabberCORE
Console.WriteLine($" Error deleting .bak files: {ex.Message}");
}
RenameExistingTxtFilesToBak(ttFolderPath);
RenameExistingTxtFilesToBak(folder);
var posts = DataAccess.GetAllPostsForBlog(blogName);
Console.WriteLine($" Found {posts.Count} post(s) for this blog.");
@@ -46,7 +69,7 @@ namespace URLNotesGrabberCORE
foreach (var typeGroup in grouped)
{
string postType = typeGroup.Key ?? "Unknown";
string outputFilePath = Path.Combine(ttFolderPath, $"{postType}.txt");
string outputFilePath = Path.Combine(folder, $"{postType}.txt");
var ordered = typeGroup.OrderBy(p => p.Date).ToList();
Console.WriteLine($" Writing {ordered.Count} post(s) to {postType}.txt");
@@ -65,10 +88,57 @@ namespace URLNotesGrabberCORE
}
}
Console.WriteLine("\nOutput mode complete.");
Console.WriteLine($"\nOutput mode complete. {writtenCount} blog(s) exported, {missingFolderCount} skipped for a missing folder.");
if (writtenCount == 0)
Console.WriteLine("Every TTFolderPath points at a folder this machine cannot see. The paths were most likely written on another machine -- re-run --updatepaths <root> here so they match local drive letters.");
return 0;
}
// Re-reads the TumblThree Index metadata into Blogs.TTFolderPath before exporting.
// A TL.db synced between machines cannot hold one absolute path that is valid on
// both, so the stored paths are only trustworthy on the machine that wrote them --
// which makes this refresh part of a normal export rather than a separate chore.
// Returns false only when the run should stop.
private static bool RefreshPaths(IConfiguration config, string[] args)
{
var settings = config.GetSection("appSettings");
if (args.Any(a => string.Equals(a, "--norefresh", StringComparison.OrdinalIgnoreCase)))
{
Console.WriteLine("Path refresh skipped (--norefresh); exporting to whatever paths TL.db already holds.");
return true;
}
string? root = args.FirstOrDefault(a => !a.StartsWith("--", StringComparison.Ordinal))
?? settings.GetValue<string>("PathTTRoot");
var result = UpdateBlogPathsRunner.Scan(root, verbose: false);
switch (result.Outcome)
{
case UpdateBlogPathsRunner.ScanOutcome.NoRootConfigured:
Console.WriteLine("No TumblThree root configured (appSettings:PathTTRoot is empty and none was passed),");
Console.WriteLine("so TTFolderPath was not refreshed. Pass one as --output <root> to refresh it.");
return true;
case UpdateBlogPathsRunner.ScanOutcome.IndexFolderMissing:
// Silently exporting stale paths here would defeat the point of folding
// the refresh in, so a bad root is a hard stop.
Console.WriteLine($"Index folder not found at: {result.IndexPath}");
Console.WriteLine("Fix the root (or pass --norefresh to export the paths already in TL.db).");
return false;
default:
Console.WriteLine($"Refreshed paths from {result.IndexPath}: " +
$"{result.MetadataFiles} metadata file(s), {result.Written} written, " +
$"{result.Unchanged} already correct, {result.NoLocation} without a location, " +
$"{result.NoMatchingRow} without a blog row, {result.Errors} error(s).");
return true;
}
}
private static void RenameExistingTxtFilesToBak(string folderPath)
{
try
+4 -2
View File
@@ -343,7 +343,7 @@ namespace URLNotesGrabberCORE
break;
case "--output":
exitCode = OutputMode.Run(config);
exitCode = OutputMode.Run(config, args.Skip(1).ToArray());
break;
case "--revert":
@@ -439,7 +439,9 @@ namespace URLNotesGrabberCORE
Console.WriteLine("--ingest [blogname]\t Ingest Tumblr .txt exports from appSettings:PathTTRoot into TL.db (all blogs, or single blog if name given)");
Console.WriteLine("--output\t Export posts from TL.db back to .txt files in each blog's TTFolderPath");
Console.WriteLine("--output [rootPath]\t Refresh Blogs.TTFolderPath from <root>\\Index (or appSettings:PathTTRoot), then export posts from TL.db back to .txt files in each blog's folder");
Console.WriteLine("--output --norefresh\t Export without refreshing TTFolderPath first");
Console.WriteLine("--revert [blogname]\t Recursively scan the PathInput tree and restore *.bak back to *.txt (current .txt saved as next-free .bkN); optional blogname filters by path substring");
+107 -13
View File
@@ -4,34 +4,64 @@ 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 static int Run(string rootPath)
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))
{
Console.WriteLine("UpdateBlogPaths: rootPath is required.");
return 1;
}
return new ScanResult { Outcome = ScanOutcome.NoRootConfigured };
DataAccess.EnsureTTFileHelperColumnsExist();
string indexPath = Path.Combine(rootPath, "Index");
if (!Directory.Exists(indexPath))
{
Console.WriteLine($"Index folder not found at: {indexPath}");
return 1;
return new ScanResult
{
Outcome = ScanOutcome.IndexFolderMissing,
RootPath = rootPath,
IndexPath = indexPath
};
}
Console.WriteLine($"Scanning Index folder: {indexPath}");
var blogFiles = Directory.GetFiles(indexPath, "*.tumblr")
.Concat(Directory.GetFiles(indexPath, "*.tmblrpriv"))
.ToList();
if (verbose)
Console.WriteLine($"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)
{
@@ -44,27 +74,91 @@ namespace URLNotesGrabberCORE
if (root.TryGetProperty("FileDownloadLocation", out JsonElement locationElement))
{
string? fileDownloadLocation = locationElement.GetString();
string? fileDownloadLocation = locationElement.GetString()?.Trim();
if (!string.IsNullOrWhiteSpace(fileDownloadLocation))
{
DataAccess.SetBlogTTFolderPath(blogName, 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($"Error processing {blogFile}: {ex.Message}");
}
}
Console.WriteLine($"\nUpdated {updatedCount} blogs with TTFolderPath");
return 0;
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;
}
}
}