mathias/hyperguild
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(watcher,api): use extract.Text() for file reading — fixes PDF ingestion

Browse Source
This commit is contained in:
Mathias Bergqvist
2026-04-23 16:01:36 +02:00
parent 53e46781b1
commit 2975eadc87
2 changed files with 11 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
ingestion/internal/watcher/watcher.go
View File

@@ -11,6 +11,7 @@ import (
"time"
"unicode"
"github.com/mathiasbq/hyperguild/ingestion/internal/extract"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
)
@@ -88,12 +89,12 @@ func processFile(ctx context.Context, cfg Config, path, date string) error {
filename := filepath.Base(path)
source := deriveSource(filename)
content, err := os.ReadFile(path)
content, err := extract.Text(path)
if err != nil {
return fmt.Errorf("read file: %w", err)
return fmt.Errorf("extract text: %w", err)
}
_, runErr := pipeline.Run(ctx, cfg.Pipeline, cfg.BrainDir, string(content), source, false)
_, runErr := pipeline.Run(ctx, cfg.Pipeline, cfg.BrainDir, content, source, false)
if runErr != nil {
// Move to failed/.
failedDir := filepath.Join(cfg.BrainDir, "raw", "failed")