Files
Christopher Poile aba4434dab MM-59966 - Compliance Export overhaul - feature branch (#29789)
* [MM-59089] Add a compliance export constant (#27919)

* add a useful constant

* i18n

* another constant

* another i18n

* [MM-60422] Add GetChannelsWithActivityDuring (#28301)

* modify GetUsersInChannelDuring to accept a slice of channelIds

* add GetChannelsWithActivityDuring

* add compliance export progress message; remove unused custom status

* linting

* tests running too fast

* add batch size config settings

* add store tests

* linting

* empty commit

* i18n changes

* fix i18n ordering

* MM-60570 - Server-side changes consolidating the export CLI with server/ent code (#28640)

* add an i18n field; add the CLI's export directory

* int64 -> int

* Add UntilUpdateAt for MessageExport and AnalyticsPostCount

to merge

* remove now-unused i18n strings

* add TranslationsPreInitFromBuffer to allow CLI to use i18n

* use GetBuilder to simplify; rename TranslationsPreInitFromFileBytes

* [MM-59089] Improve compliance export timings (#1733 - Enterprise repo)

* MM-60422 - Performance and logic fixes for Compliance Exports (#1757 - Enterprise repo)

* MM-60570 - Enterprise-side changes consolidating the export CLI with server/ent code (#1769 - Enterprise repo)

* merge conflicts; missed file from ent branch

* MM-61038 - Add an option to sqlstore.New (#28702)

remove useless comment

add test

add an option to sqlstore.New

* MM-60976: Remove RunExport command from Mattermost binary (#28805)

* remove RunExport command from mattermost binary

* remove the code it was calling

* fix i18n

* remove test (was only testing license, not functionality)

* empty commit

* fix flaky GetChannelsWithActivityDuring test

* MM-60063: Dedicated Export Filestore fix, redo of #1772 (enterprise) (#28803)

* redo filestore fix #1772 (enterprise repo) on top of MM-59966 feature

* add new e2e tests for export filestore

* golint

* ok, note to self: shadowing bad, actually (when there's a defer)

* empty commit

* MM-61137 - Message export: Support 7.8.11 era dbs (#28824)

* support 7.8.11 era dbs by wrapping the store using only what we need

* fix flaky GetChannelsWithActivityDuring test

* add a comment

* only need to define the MEFileInfoStore (the one that'll be overridden)

* blank commit

* MM-60974 - Message Export: Add performance metrics (#28836)

* support 7.8.11 era dbs by wrapping the store using only what we need

* fix flaky GetChannelsWithActivityDuring test

* add a comment

* only need to define the MEFileInfoStore (the one that'll be overridden)

* performance metrics

* cleanup unneeded named returns

* blank commit

* MM-60975 - Message export: Add startTime and endTime to export folder name (#28840)

* support 7.8.11 era dbs by wrapping the store using only what we need

* fix flaky GetChannelsWithActivityDuring test

* add a comment

* only need to define the MEFileInfoStore (the one that'll be overridden)

* performance metrics

* output startTime and endTime in export folder

* empty commit

* merge conflict

* MM-60978 - Message export: Improve xml fields; fix delete semantics (#28873)

* support 7.8.11 era dbs by wrapping the store using only what we need

* fix flaky GetChannelsWithActivityDuring test

* add a comment

* only need to define the MEFileInfoStore (the one that'll be overridden)

* performance metrics

* output startTime and endTime in export folder

* empty commit

* add xml fields, omit when empty, tests

* fix delete semantics; test (and test for update semantics)

* clarify comments

* simplify edited post detection, now there's no edge case.

* add some spacing to help fast running tests

* merge conflicts/updates needed for new deleted post semantics

* linting; fixing tests from upstream merge

* use SafeDereference

* linting

* stronger typing; better wrapped errors; better formatting

* blank commit

* goimports formatting

* fix merge mistake

* minor fixes due to changes in master

* MM-61755 - Simplifying and Support reporting to the db from the CLI (#29281)

* finally clean up JobData struct and stringMap; prep for CLI using db

* and now simplify using StringMapToJobDataWithZeroValues

* remove unused fn

* create JobDataExported; clean up errors

* MM-60176 - Message Export: Global relay cleanup (#29168)

* move global relay logic into global_relay_export

* blank commit

* blank commit

* improve errors

* MM-60693 - Refactor CSV to use same codepath as Actiance (#29191)

* move global relay logic into global_relay_export

* blank commit

* refactor (and simplify) ExportParams into shared

* blank commit

* remove unused fn

* csv now uses pre-calculated joins/leaves like actiance

* improve errors

* remove nil post check; remove ignoredPosts metric

* remove unneeded copy

* MM-61696 - Refactor GlobalRelay to use same codepath as Actiance (#29225)

* move global relay logic into global_relay_export

* blank commit

* refactor (and simplify) ExportParams into shared

* blank commit

* remove unused fn

* csv now uses pre-calculated joins/leaves like actiance

* remove newly unneeded function and its test. goodbye.

* refactor GetPostAttachments for csv + global relay to share

* refactor global_relay_export and fix tests (no changes to output)

* improve errors

* remove nil post check; remove ignoredPosts metric

* remove unneeded copy

* remove unneeded nil check

* PR comments

* MM-61715 - Generalize e2e to all export types 🤖  (#29369)

* move global relay logic into global_relay_export

* blank commit

* refactor (and simplify) ExportParams into shared

* blank commit

* remove unused fn

* csv now uses pre-calculated joins/leaves like actiance

* remove newly unneeded function and its test. goodbye.

* refactor GetPostAttachments for csv + global relay to share

* refactor global_relay_export and fix tests (no changes to output)

* improve errors

* remove nil post check; remove ignoredPosts metric

* remove unneeded copy

* remove unneeded nil check

* PR comments

* refactor isDeletedMsg for all export types

* fix start and endtime, nasty csv createAt bug; bring closer to Actiance

* align unit tests with new logic (e.g. starttime / endtime)

* refactor a TimestampConvert fn for code + tests

* bug: pass templates to global relay (hurray for e2e tests, otherwise...)

* add global relay zip to allowed list (only for tests)

* test helpers

* new templates for e2e tests

* e2e tests... phew.

* linting

* merge conflicts

* unexport PostToRow; add test helper marker

* cleanup, shortening, thanks to PR comments

* MM-61972 - Generalize export data path - Actiance (#29399)

* extract and generalize the export data generation functions

* finish moving test (bc of previous extraction)

* lift a function from common -> shared (to break an import cycle)

* actiance now takes general export data, processes it into actiance data

* bring tests in line with correct sorting rules (upadateAt, messageId)

* fixups, PR comments

* turn strings.Repeat into a more descriptive const

amended: one letter fix; bad rebase

* MM-62009 - e2e clock heisenbug (#29434)

* consolidate assertions; output debuggable diffs (keeping for future)

* refactor test output generator to generators file

* waitUntilZeroPosts + pass through until to job = fix all clock issues

* simplify messages to model.NewId(); remove unneeded waitUntilZeroPosts

* model.NewId() -> storetest.NewTestID()

* MM-61980 - Generalize export data path - CSV (#29482)

* simple refactoring

* increase sleep times for (very) rare test failures

* add extra information to the generic export for CSV

* adj Actiance to handle new generic export (no difference in its output)

* no longer need mergePosts (yay), move getJoinLeavePosts for everyone

* adjust tests for new csv semantics (detailed in summary)

* and need to add the new exported data to the export_data_tests

* rearrange csv writing to happen after data export (more logical)

* linting

* remove debug statements

* figured out what was wrong with global relay e2e test 3; solid now

* PR comments

* MM-61718 - Generalize export data path - Global Relay (#29508)

* move global relay over to using the generalized export data

* performance pass -- not much can be done

* Update server/enterprise/message_export/global_relay_export/global_relay_export.go

Co-authored-by: Claudio Costa <cstcld91@gmail.com>

---------

Co-authored-by: Claudio Costa <cstcld91@gmail.com>

* MM-62058 - Align CSV with Actiance (#29551)

* refactoring actiance files and var names for clarity

* bug found in exported attachments (we used to miss some start/ends)

* changes needed for actiance due to new generic exports

* bringing CSV up to actiance standards

* fixing global relay b/c of new semantics (adding a note on an edge case)

* aligning e2e tests, adding comments to clarify what is expected/tested

* necessary changes; 1 more test for added functionality (ignoreDeleted)

* comment style

* MM-62059 - Align Global Relay with Actiance/CSV; many fixes (#29665)

* core logic changes to general export_data and the specific export paths

* unit tests and e2e tests, covering all new edge cases and all logic

* linting

* better var naming, const value, and cleaning up functions calls

* MM-62436 - Temporarily skip cypress tests that require download link (#29772)

---------

Co-authored-by: Claudio Costa <cstcld91@gmail.com>
2025-01-10 16:56:02 -05:00

189 строки
5.9 KiB
Go

// Copyright (c) 2015-present Mattermost, Inc. All Rights Reserved.
// See LICENSE.txt for license information.
package commands
import (
"context"
"os"
"path/filepath"
"time"
"github.com/mattermost/mattermost/server/public/model"
"github.com/mattermost/mattermost/server/public/shared/request"
"github.com/mattermost/mattermost/server/v8/channels/app"
"github.com/mattermost/mattermost/server/v8/channels/audit"
"github.com/pkg/errors"
"github.com/spf13/cobra"
)
var ExportCmd = &cobra.Command{
Use: "export",
Short: "Export data from Mattermost",
Long: "Export data from Mattermost in a format suitable for import into a third-party application or another Mattermost instance",
}
var ScheduleExportCmd = &cobra.Command{
Use: "schedule",
Short: "Schedule an export data job in Mattermost",
Long: "Schedule an export data job in Mattermost (this will run asynchronously via a background worker)",
Example: "export schedule --format=actiance --exportFrom=12345 --timeoutSeconds=12345",
RunE: scheduleExportCmdF,
}
var BulkExportCmd = &cobra.Command{
Use: "bulk [file]",
Short: "Export bulk data.",
Long: "Export data to a file compatible with the Mattermost Bulk Import format.",
Example: "export bulk bulk_data.json",
RunE: bulkExportCmdF,
Args: cobra.ExactArgs(1),
}
func init() {
ScheduleExportCmd.Flags().String("format", "actiance", "The format to export data")
ScheduleExportCmd.Flags().Int64("exportFrom", -1, "The timestamp of the earliest post to export, expressed in seconds since the unix epoch.")
ScheduleExportCmd.Flags().Int("timeoutSeconds", -1, "The maximum number of seconds to wait for the job to complete before timing out.")
BulkExportCmd.Flags().Bool("all-teams", true, "Export all teams from the server.")
BulkExportCmd.Flags().Bool("with-archived-channels", false, "Also exports archived channels.")
BulkExportCmd.Flags().Bool("with-profile-pictures", false, "Also exports profile pictures.")
BulkExportCmd.Flags().Bool("attachments", false, "Also export file attachments.")
BulkExportCmd.Flags().Bool("archive", false, "Outputs a single archive file.")
ExportCmd.AddCommand(ScheduleExportCmd)
ExportCmd.AddCommand(BulkExportCmd)
RootCmd.AddCommand(ExportCmd)
}
func scheduleExportCmdF(command *cobra.Command, args []string) error {
a, err := InitDBCommandContextCobra(command, app.SkipPostInitialization())
if err != nil {
return err
}
defer a.Srv().Shutdown()
if !*a.Config().MessageExportSettings.EnableExport {
return errors.New("ERROR: The message export feature is not enabled")
}
var rctx request.CTX = request.EmptyContext(a.Log())
// for now, format is hard-coded to actiance. In time, we'll have to support other formats and inject them into job data
format, err := command.Flags().GetString("format")
if err != nil {
return errors.New("format flag error")
}
if format != "actiance" {
return errors.New("unsupported export format")
}
startTime, err := command.Flags().GetInt64("exportFrom")
if err != nil {
return errors.New("exportFrom flag error")
}
if startTime < 0 {
return errors.New("exportFrom must be a positive integer")
}
timeoutSeconds, err := command.Flags().GetInt("timeoutSeconds")
if err != nil {
return errors.New("timeoutSeconds error")
}
if timeoutSeconds < 0 {
return errors.New("timeoutSeconds must be a positive integer")
}
if messageExportI := a.MessageExport(); messageExportI != nil {
ctx := context.Background()
if timeoutSeconds > 0 {
var cancel context.CancelFunc
ctx, cancel = context.WithTimeout(ctx, time.Second*time.Duration(timeoutSeconds))
defer cancel()
}
rctx = rctx.WithContext(ctx)
job, err := messageExportI.StartSynchronizeJob(rctx, startTime)
if err != nil || job.Status == model.JobStatusError || job.Status == model.JobStatusCanceled {
CommandPrintErrorln("ERROR: Message export job failed. Please check the server logs")
} else {
CommandPrettyPrintln("SUCCESS: Message export job complete")
auditRec := a.MakeAuditRecord(rctx, "scheduleExport", audit.Success)
auditRec.AddMeta("format", format)
auditRec.AddMeta("start", startTime)
a.LogAuditRec(rctx, auditRec, nil)
}
}
return nil
}
func bulkExportCmdF(command *cobra.Command, args []string) error {
a, err := InitDBCommandContextCobra(command, app.SkipPostInitialization())
if err != nil {
return err
}
defer a.Srv().Shutdown()
rctx := request.EmptyContext(a.Log())
allTeams, err := command.Flags().GetBool("all-teams")
if err != nil {
return errors.Wrap(err, "all-teams flag error")
}
if !allTeams {
return errors.New("Nothing to export. Please specify the --all-teams flag to export all teams.")
}
attachments, err := command.Flags().GetBool("attachments")
if err != nil {
return errors.Wrap(err, "attachments flag error")
}
archive, err := command.Flags().GetBool("archive")
if err != nil {
return errors.Wrap(err, "archive flag error")
}
withArchivedChannels, err := command.Flags().GetBool("with-archived-channels")
if err != nil {
return errors.Wrap(err, "with-archived-channels flag error")
}
includeProfilePictures, err := command.Flags().GetBool("with-profile-pictures")
if err != nil {
return errors.Wrap(err, "with-profile-pictures flag error")
}
fileWriter, err := os.Create(args[0])
if err != nil {
return err
}
defer fileWriter.Close()
outPath, err := filepath.Abs(args[0])
if err != nil {
return err
}
var opts model.BulkExportOpts
opts.IncludeAttachments = attachments
opts.CreateArchive = archive
opts.IncludeArchivedChannels = withArchivedChannels
opts.IncludeProfilePictures = includeProfilePictures
if err := a.BulkExport(rctx, fileWriter, filepath.Dir(outPath), nil /* nil job since it's spawned from CLI */, opts); err != nil {
CommandPrintErrorln(err.Error())
return err
}
auditRec := a.MakeAuditRecord(rctx, "bulkExport", audit.Success)
auditRec.AddMeta("all_teams", allTeams)
auditRec.AddMeta("file", args[0])
a.LogAuditRec(rctx, auditRec, nil)
return nil
}