Files
job-search/internal/cli/fetch/fts_once.go
T
bwilliams c09c30ae71 Added a backfill in 7-day windows, and fetches now keep their data on a failure
Backfilling a long window (an early --since, or a long time offline)
hit the API's rate limit, which could still be exceeded after waiting
once, and then everything fetched so far was lost.

Before each Find a Tender source's worker starts, a start point more
than 7 days ago is now backfilled in 7-day windows bounded on both
sides, oldest first, each saved before the next is fetched. A window
that fails is saved as far as it got and fetched again from its start
after the source's interval. The worker then carries on from the end
of the last window.

A 429 is now waited out up to sources.<source>.rate_limit_retries
times (default 5) rather than once; fts-once --ignore-rate-limit uses
0. FetchAll returns what it fetched before an error along with it, and
the workers save it, so a failed run no longer loses its data.
findatender's FetchAll and FetchOnce take RequestOptions, which gains
Until (updatedTo), and RateLimitRetries replaces AllowRateLimit.
2026-10-21 12:40:39 +01:00

157 lines
4.0 KiB
Go

package fetch
import (
"encoding/json"
"errors"
"fmt"
"log/slog"
"slices"
"time"
"github.com/spf13/cobra"
"git.avsdev.uk/Go/job-search/internal/cli"
"git.avsdev.uk/Go/job-search/internal/findatender"
"git.avsdev.uk/Go/job-search/internal/types"
)
// Release tags for each stage of a procedure, from the OCDS releaseTag
// codelist. Cancellations are left out, as a cancelled procedure is no longer
// at any stage.
var stageTags = map[string][]string{
"planning": {"planning", "planningUpdate"},
"opportunity": {"tender", "tenderAmendment", "tenderUpdate"},
"award": {
"award", "awardUpdate",
"contract", "contractUpdate", "contractAmendment",
"implementation", "implementationUpdate", "contractTermination",
},
}
// filter keeps the opportunities whose latest release is at stage. Releases
// are oldest first, so the last one is the procedure's current stage.
func filter(
opportunities []*types.Opportunity, stage string,
) []*types.Opportunity {
var matching []*types.Opportunity
for _, opportunity := range opportunities {
if len(opportunity.Releases) == 0 {
continue
}
latest := opportunity.Releases[len(opportunity.Releases)-1]
for _, tag := range latest.Tags {
if slices.Contains(stageTags[stage], tag.Tag) {
matching = append(matching, opportunity)
break
}
}
}
return matching
}
// commandFTSOnce returns the "fts-once" command, which fetches from Find a
// Tender once and prints the releases as JSON.
func commandFTSOnce(opts *cli.Options) *cobra.Command {
cmd := &cobra.Command{
Use: "fts-once",
Short: "Fetch from Find a Tender once and print the releases as JSON",
PersistentPreRun: func(cmd *cobra.Command, args []string) {
slog.Debug("command persistent pre-run", "command", "fts-once")
},
PersistentPostRun: func(cmd *cobra.Command, args []string) {
slog.Debug("command persistent post-run", "command", "fts-once")
},
RunE: func(cmd *cobra.Command, args []string) error {
slog.Debug("command run", "command", "fts-once")
conf, err := opts.RunSetup(cmd, true, true)
if err != nil {
return fmt.Errorf("load configuration: %w", err)
}
since, sinceErr := cmd.Flags().GetTime("since")
if sinceErr != nil {
return sinceErr
}
if conf.Sources.FindATender.APIRoot == "" {
return errors.New("sources.find_a_tender.api_root is not set")
}
findATender := findatender.New(conf.Sources.FindATender.APIRoot)
defer findATender.Shutdown()
ignoreRateLimit, _ := cmd.Flags().GetBool("ignore-rate-limit")
rateLimitRetries := conf.Sources.FindATender.RateLimitRetries
if ignoreRateLimit {
rateLimitRetries = 0
}
results, err := findATender.FetchAll(findatender.RequestOptions{
Since: since,
RateLimitRetries: rateLimitRetries,
})
if err != nil {
return err
}
planning, _ := cmd.Flags().GetBool("planning")
opportunities, _ := cmd.Flags().GetBool("opportunities")
awards, _ := cmd.Flags().GetBool("awards")
filterTag := ""
if planning {
filterTag = "planning"
}
if opportunities {
filterTag = "opportunity"
}
if awards {
filterTag = "award"
}
if filterTag != "" {
results = filter(results, filterTag)
}
encoded, err := json.MarshalIndent(results, "", " ")
if err != nil {
return err
}
fmt.Println(string(encoded))
return nil
},
}
cmd.Flags().Time(
"since",
time.Time{},
[]string{
time.DateOnly, time.DateTime,
},
"contract updates published since YYYY-MM-DD[ hh:mm:ss]",
)
cmd.Flags().Bool(
"planning",
false,
"only return planning (i.e. exclude opportunities and awards)",
)
cmd.Flags().Bool(
"opportunities",
false,
"only return opportunities (i.e. exclude awards and planning)",
)
cmd.Flags().Bool(
"awards",
false,
"only return awards (i.e. exclude planning and opportunities)",
)
cmd.Flags().Bool(
"ignore-rate-limit", false, "ignore the rate limit and fail if exceeded",
)
cmd.MarkFlagsMutuallyExclusive("planning", "opportunities", "awards")
return cmd
}