Files
finance-duck/internal/app/reclassify.go
T

204 lines
6.1 KiB
Go

package app
import (
"context"
"errors"
"reflect"
"slices"
"strings"
"time"
"finance-duck/internal/domain"
)
type Fields struct {
Merchant bool `json:"merchant"`
Category bool `json:"category"`
Tags bool `json:"tags"`
}
type PreviewRequest struct {
Revision string `json:"revision"`
From string `json:"from"`
To string `json:"to"`
Model string `json:"model"`
Fields Fields `json:"fields"`
}
type Change struct {
ID string `json:"id"`
Description string `json:"description"`
Before domain.Enrichment `json:"before"`
After domain.Enrichment `json:"after"`
}
type ClassificationError struct {
ID string `json:"id"`
Error string `json:"error"`
}
type Preview struct {
ID string `json:"id"`
Revision string `json:"revision"`
Changes []Change `json:"changes"`
Analysed int `json:"analysed"`
Unchanged int `json:"unchanged"`
Errors []ClassificationError `json:"errors"`
NewMerchants []domain.Merchant `json:"new_merchants"`
created time.Time
}
func validRange(from, to string) error {
f, e := time.Parse("2006-01-02", from)
if e != nil {
return errors.New("from must be YYYY-MM-DD")
}
t, e := time.Parse("2006-01-02", to)
if e != nil {
return errors.New("to must be YYYY-MM-DD")
}
if f.After(t) {
return errors.New("from must not exceed to")
}
return nil
}
func (a *App) Preview(ctx context.Context, r PreviewRequest) (Preview, error) {
if err := validRange(r.From, r.To); err != nil {
return Preview{}, err
}
if !r.Fields.Merchant && !r.Fields.Category && !r.Fields.Tags {
return Preview{}, errors.New("select at least one enrichment field")
}
if strings.TrimSpace(r.Model) == "" {
return Preview{}, errors.New("model is required")
}
a.mu.Lock()
s, err := a.snapshot(ctx)
client := a.classifier.WithModel(r.Model)
a.mu.Unlock()
if err != nil {
return Preview{}, err
}
if r.Revision != s.Revision {
return Preview{}, errors.New("revision conflict: reload before analysing")
}
p := Preview{ID: domain.NewID("preview"), Revision: s.Revision, Changes: []Change{}, Errors: []ClassificationError{}, created: time.Now()}
baseMerchants := len(s.Data.Merchants)
for _, t := range s.Data.Transactions {
if t.Facts.BookingDate < r.From || t.Facts.BookingDate > r.To || t.Enrichment.Kind == "transfer" || t.Enrichment.Kind == domain.KindInvestment {
continue
}
if err = ctx.Err(); err != nil {
return Preview{}, err
}
p.Analysed++
proposal, e := client.Classify(ctx, t.Facts, s.Data, true)
if err = ctx.Err(); err != nil {
return Preview{}, err
}
if e != nil {
p.Errors = append(p.Errors, ClassificationError{t.Facts.ID, e.Error()})
continue
}
after := t.Enrichment
if r.Fields.Merchant {
after.MerchantID = proposal.Enrichment.MerchantID
if e = addProposal(&s.Data, proposal, t.Facts); e != nil {
p.Errors = append(p.Errors, ClassificationError{t.Facts.ID, e.Error()})
continue
}
}
if r.Fields.Category {
after.CategoryID = proposal.Enrichment.CategoryID
}
if r.Fields.Tags {
after.TagIDs = slices.Clone(proposal.Enrichment.TagIDs)
}
if e = domain.ValidateEnrichment(s.Data, t.Facts, after); e != nil {
p.Errors = append(p.Errors, ClassificationError{t.Facts.ID, e.Error()})
continue
}
beforeComparable, afterComparable := t.Enrichment, after
beforeComparable.Classification = domain.Provenance{}
afterComparable.Classification = domain.Provenance{}
beforeComparable.TagIDs = slices.Clone(beforeComparable.TagIDs)
afterComparable.TagIDs = slices.Clone(afterComparable.TagIDs)
slices.Sort(beforeComparable.TagIDs)
slices.Sort(afterComparable.TagIDs)
if reflect.DeepEqual(beforeComparable, afterComparable) {
p.Unchanged++
continue
}
after.Classification = proposal.Enrichment.Classification
p.Changes = append(p.Changes, Change{t.Facts.ID, t.Facts.RawDescription, t.Enrichment, after})
}
p.NewMerchants = append([]domain.Merchant{}, s.Data.Merchants[baseMerchants:]...)
a.mu.Lock()
defer a.mu.Unlock()
for id, old := range a.previews {
if time.Since(old.created) > time.Hour {
delete(a.previews, id)
}
}
if len(a.previews) >= 20 {
return Preview{}, errors.New("too many active previews; cancel one first")
}
a.previews[p.ID] = p
return p, nil
}
func (a *App) ApplyPreview(ctx context.Context, id, rev string, ids []string) (State, error) {
a.mu.Lock()
defer a.mu.Unlock()
p, ok := a.previews[id]
if !ok || time.Since(p.created) > time.Hour {
return State{}, errors.New("preview expired or unknown; analyse again")
}
if rev != p.Revision {
return State{}, errors.New("revision conflict: preview was generated from different records")
}
s, err := a.snapshot(ctx)
if err != nil {
return State{}, err
}
if s.Revision != rev {
return State{}, errors.New("revision conflict: data changed after preview; analyse again")
}
changes := map[string]domain.Enrichment{}
for _, c := range p.Changes {
changes[c.ID] = c.After
}
selected := map[string]bool{}
for _, id := range ids {
if _, ok := changes[id]; !ok {
return State{}, errors.New("selected transaction is not in preview")
}
selected[id] = true
}
if len(selected) == 0 {
return State{}, errors.New("select at least one change")
}
needed := map[string]bool{}
for i, t := range s.Data.Transactions {
if !selected[t.Facts.ID] {
continue
}
s.Data.Transactions[i].Enrichment = changes[t.Facts.ID]
needed[changes[t.Facts.ID].MerchantID] = true
}
for _, m := range p.NewMerchants {
if needed[m.ID] {
s.Data.Merchants = append(s.Data.Merchants, m)
}
}
for _, t := range s.Data.Transactions {
if selected[t.Facts.ID] && t.Enrichment.MerchantID != "" {
// New merchants already carry their first alias; existing merchants
// learn only when the real matcher stays unambiguous.
LearnAlias(&s.Data, t.Facts, t.Enrichment.MerchantID)
}
}
state, err := a.commit(ctx, rev, s.Data)
if err != nil {
return State{}, err
}
delete(a.previews, id)
return state, nil
}
func (a *App) CancelPreview(id string) { a.mu.Lock(); defer a.mu.Unlock(); delete(a.previews, id) }