thomas/multiarch-docker-images
1
0
Fork 0
mirror of https://github.com/napnap75/multiarch-docker-images.git synced 2026-11-13 09:31:46 +01:00
Code Issues Projects Releases Wiki Activity

Corrections after first run

Browse Source
This commit is contained in:
thomas
2026-11-03 22:36:27 +01:00
parent 6f94674fc9
commit 02f7fd99bb
15 changed files with 268 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
archivist/internal/pipeline/pipeline.go
+10 -6
View File
@@ -8,8 +8,8 @@ import (
"fmt"
"strings"
ganigeorgiev.com/pocketbase/dbx"
ganigeorgiev.com/pocketbase/pocketbase/core"
"ganigeorgiev.com/pocketbase/dbx"
"ganigeorgiev.com/pocketbase/pocketbase/core"
"github.com/ledongthuc/pdf"
"github.com/napnap75/archivist/internal/config"
"github.com/napnap75/archivist/internal/pbapp"
@@ -24,7 +24,7 @@ type pollState struct {
var stable = map[string]pollState{}
func RunPoll(app *core.App, cfg *config.Config, s3 *storage.Client) {
func RunPoll(app core.App, cfg *config.Config, s3 *storage.Client) {
ctx := context.Background()
// US-11: recover interrupted filings first.
@@ -54,7 +54,7 @@ func RunPoll(app *core.App, cfg *config.Config, s3 *storage.Client) {
}
}
func processOne(app *core.App, cfg *config.Config, s3 *storage.Client, ctx context.Context, key string) error {
func processOne(app core.App, cfg *config.Config, s3 *storage.Client, ctx context.Context, key string) error {
// US-12: download in memory, sha256 on the fly.
data, hash, err := s3.Get(ctx, key)
if err != nil {
@@ -154,7 +154,7 @@ func fileDocument(s3 *storage.Client, ctx context.Context, record *core.Record,
// recoverStuck completes interrupted filings: records whose file_key is still
// under inbox/ (US-11).
func recoverStuck(app *core.App, cfg *config.Config, s3 *storage.Client, ctx context.Context) {
func recoverStuck(app core.App, cfg *config.Config, s3 *storage.Client, ctx context.Context) {
stuck, err := app.FindRecordsByFilter("documents", "file_key ~ {:p}", "", 100, 0, dbx.Params{"p": "inbox/"})
if err != nil {
app.Logger().Error("recovery: query failed", "error", err)
@@ -213,7 +213,11 @@ func extractPages(data []byte) ([]string, error) {
if p.V.IsNull() {
return nil, fmt.Errorf("page %d is null", i)
}
pages = append(pages, p.GetPlainText(nil))
text, err := p.GetPlainText(nil)
if err != nil {
return nil, fmt.Errorf("page %d: %w", i, err)
}
pages = append(pages, text)
}
if len(pages) == 0 {
return nil, fmt.Errorf("no page extracted")