jim/URLNotesGrabberCore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: merge ThreeTxtFileHelper into URLNotesGrabberCORE

Browse Source 
Folds the standalone ThreeTxtFileHelper tool into URLNotesGrabberCORE so
text-file ingest/output/correct lives alongside the API scraper. Adds
new flags -ingest, -output, -correct (with -apply), -updatepaths, and a
one-time -importposts <posts.db> migration.

Schema: Blogs.TTFolderPath and Posts.PostType are added by an idempotent
migration. On (BlogName, PostID) collisions, content columns are
overwritten while engagement columns (ByLikes, RootBlogName, RootURL,
HasNotesGathered, NotFound, NotesGatheredDateTime, Likes*) are preserved.

Co-Authored-By: Claude Opus 4.7 <[email protected]>
This commit is contained in:
jim
2026-05-18 12:43:17 -05:00
co-authored by Claude Opus 4.7
parent 5781e121d2
commit 3aff849216
10 changed files with 1419 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
URLNotesGrabberCORE/Program.cs
+48
View File
@@ -181,6 +181,18 @@ namespace URLNotesGrabberCORE
Console.WriteLine("-api [section]\t Use a specific API settings section from appsettings.json (e.g. TumblrApi3)");
Console.WriteLine("-ingest [path]\t Ingest Tumblr .txt exports under path (or appSettings:PathTTRoot) into TL.db");
Console.WriteLine("-output\t Export posts from TL.db back to .txt files in each blog's TTFolderPath");
Console.WriteLine("-correct [bakPath]\t Dry-run: report multi-line field updates available from a BAK directory");
Console.WriteLine("-correct -apply [bakPath]\t Apply BAK-file corrections to matching posts (prompts yes/no)");
Console.WriteLine("-updatepaths [rootPath]\t Read .tumblr/.tmblrpriv metadata from <root>\\Index and set Blogs.TTFolderPath");
Console.WriteLine("-importposts [path-to-posts.db]\t One-time migration: copy legacy ThreeTxtFileHelper posts.db rows into TL.db");
break;
case "-parse":
@@ -309,6 +321,42 @@ namespace URLNotesGrabberCORE
DumpUrls(settings.GetValue<string>("PathOutputUrls"));
break;
case "-ingest":
IngestMode.Run(config, args.Skip(1).ToArray());
break;
case "-output":
OutputMode.Run(config);
break;
case "-correct":
{
bool applyChanges = args.Skip(1).Any(a => string.Equals(a, "-apply", StringComparison.OrdinalIgnoreCase) || string.Equals(a, "--apply", StringComparison.OrdinalIgnoreCase));
var correctArgs = args.Skip(1)
.Where(a => !string.Equals(a, "-apply", StringComparison.OrdinalIgnoreCase) && !string.Equals(a, "--apply", StringComparison.OrdinalIgnoreCase))
.ToArray();
CorrectMode.Run(config, correctArgs, applyChanges);
break;
}
case "-updatepaths":
{
string rootPath = args.Length > 1 ? args[1] : (settings.GetValue<string>("PathTTRoot") ?? settings.GetValue<string>("PathInput") ?? string.Empty);
UpdateBlogPathsRunner.Run(rootPath);
break;
}
case "-importposts":
{
if (args.Length < 2)
{
Console.WriteLine("Usage: -importposts <path-to-legacy-posts.db>");
break;
}
LegacyPostsDbImporter.Run(args[1]);
break;
}
default:
Console.WriteLine("** Unknown Command ** " + args[0]);
break;