diff --git a/assets/less/cds-rdm/administration/harvester-reports.less b/assets/less/cds-rdm/administration/harvester-reports.less index 12a16ecb..2629424e 100644 --- a/assets/less/cds-rdm/administration/harvester-reports.less +++ b/assets/less/cds-rdm/administration/harvester-reports.less @@ -53,4 +53,29 @@ color: #999; margin-top: 0.2em; } -} \ No newline at end of file +} + +.harvester-run-success-message { + white-space: normal; + text-align: left; +} + +// Job run report: wrap long lines; scroll region height (matches admin log-table intent) +.harvester-run-log-report { + width: 100%; + + .harvester-run-log-table.log-table { + max-height: calc(100vh - 11rem); + overflow-x: hidden; + } + + .harvester-run-log-segment { + overflow-x: hidden; + } + + .log-line .log-message { + white-space: pre-wrap; + overflow-wrap: anywhere; + word-break: break-word; + } +} diff --git a/site/cds_rdm/administration/harvester_reports.py b/site/cds_rdm/administration/harvester_reports.py index e78a25fd..055b58b7 100644 --- a/site/cds_rdm/administration/harvester_reports.py +++ b/site/cds_rdm/administration/harvester_reports.py @@ -6,17 +6,40 @@ # under the terms of the GPL-2.0 License; see LICENSE file for more details. """Harvester Reports administration views.""" - import json from functools import partial -from flask import current_app +from flask import Blueprint, abort, current_app, render_template, request from invenio_administration.views.base import AdminResourceListView from invenio_i18n import lazy_gettext as _ from invenio_jobs.models import Job, Run from invenio_search_ui.searchconfig import search_app_config from cds_rdm.administration.permissions import curators_permission +from cds_rdm.harvester_runs.logs import HarvesterRunError, report_context + + +def create_harvester_report_blueprint(app): + """Create the harvester run report UI blueprint.""" + blueprint = Blueprint("cds_rdm_harvester_report_page", __name__) + + def harvester_report_not_found(_error): + return render_template(current_app.config["THEME_404_TEMPLATE"]), 404 + + @blueprint.route("/administration/harvester-reports//report") + @curators_permission.require(http_exception=403) + def harvester_run_report(run_id): + try: + ctx = report_context(str(run_id)) + except HarvesterRunError as error: + abort(error.code) + return render_template( + "cds_rdm/administration/harvester_run_report.html", + **ctx, + ) + + blueprint.register_error_handler(404, harvester_report_not_found) + return blueprint class HarvesterReportsView(AdminResourceListView): @@ -106,8 +129,13 @@ def get_context(self, **kwargs): job_id = self._get_inspire_job_id() if job_id: runs = self._fetch_recent_runs(job_id, limit=20) + requested_run_id = request.args.get("run_id") + default_run = next( + (run for run in runs if run["id"] == requested_run_id), + runs[0] if runs else None, + ) context["harvester_runs"] = json.dumps(runs) - context["default_run"] = json.dumps(runs[0]) if runs else None + context["default_run"] = json.dumps(default_run) if default_run else None else: context["harvester_runs"] = json.dumps([]) context["default_run"] = None diff --git a/site/cds_rdm/assets/semantic-ui/js/cds_rdm/administration/harvesterReports/DownloadButton.js b/site/cds_rdm/assets/semantic-ui/js/cds_rdm/administration/harvesterReports/DownloadButton.js index 8ca4c67a..33835128 100644 --- a/site/cds_rdm/assets/semantic-ui/js/cds_rdm/administration/harvesterReports/DownloadButton.js +++ b/site/cds_rdm/assets/semantic-ui/js/cds_rdm/administration/harvesterReports/DownloadButton.js @@ -5,39 +5,43 @@ // under the terms of the GPL-2.0 License; see LICENSE file for more details. import React from "react"; -import { withState } from "react-searchkit"; import { Button, Icon } from "semantic-ui-react"; import { i18next } from "@translations/invenio_administration/i18next"; -import { extractRunIdFromQuery } from "./utils"; -const DownloadButtonComponent = ({ currentQueryState }) => { - const domContainer = document.getElementById("invenio-search-config"); - const runs = JSON.parse(domContainer?.dataset.harvesterRuns || "[]"); - - const runId = extractRunIdFromQuery( - currentQueryState.queryString || "", - runs - ); - - const handleDownload = () => { - if (!runId) return; - const params = new URLSearchParams({ run_id: runId }); - window.location.href = `/harvester-reports/download?${params.toString()}`; - }; - - return ( - - ); -}; - -export const DownloadButton = withState(DownloadButtonComponent); +export const DownloadButton = ({ runId }) => ( +
+
+ +
+
+ +
+
+); diff --git a/site/cds_rdm/assets/semantic-ui/js/cds_rdm/administration/harvesterReports/SearchBar.js b/site/cds_rdm/assets/semantic-ui/js/cds_rdm/administration/harvesterReports/SearchBar.js index ad37da32..a51c6aa5 100644 --- a/site/cds_rdm/assets/semantic-ui/js/cds_rdm/administration/harvesterReports/SearchBar.js +++ b/site/cds_rdm/assets/semantic-ui/js/cds_rdm/administration/harvesterReports/SearchBar.js @@ -28,18 +28,15 @@ const SearchBarComponent = ({ updateQueryState, currentQueryState }) => { const { sortOptions, sortOrderDisabled } = useContext(SearchConfigurationContext); - // Derive selected run from the timestamp in the current query — null if user typed a custom range - const runIdFromQuery = extractRunIdFromQuery(currentQueryState.queryString, runs); - const selectedRun = runs.find((r) => r.id === runIdFromQuery) || null; + const [activeRunId, setActiveRunId] = React.useState(() => defaultRun?.id ?? null); - const [inputValue, setInputValue] = React.useState(currentQueryState.queryString || ""); + const runIdFromQuery = extractRunIdFromQuery(currentQueryState.queryString, runs); + const effectiveRunId = runIdFromQuery || activeRunId; + const selectedRun = runs.find((r) => r.id === effectiveRunId) || null; - // Auto-select default run on mount only if there is no existing query - React.useEffect(() => { - if (!currentQueryState.queryString && defaultRun) { - executeSearch(defaultRun, ""); - } - }, []); + const [inputValue, setInputValue] = React.useState( + currentQueryState.queryString || "" + ); const executeSearch = (run, userInput) => { const timestampFilter = buildTimestampFilter(run); @@ -57,9 +54,23 @@ const SearchBarComponent = ({ updateQueryState, currentQueryState }) => { }); }; + React.useEffect(() => { + const q = currentQueryState.queryString || ""; + const fromQuery = extractRunIdFromQuery(q, runs); + if (fromQuery) { + setActiveRunId(fromQuery); + } else if (!q && defaultRun) { + setActiveRunId(defaultRun.id); + executeSearch(defaultRun, ""); + } + }, []); + const onRunChange = (e, { value }) => { + setActiveRunId(value || null); const run = runs.find((r) => r.id === value); - executeSearch(run, ""); + if (run) { + executeSearch(run, ""); + } }; const onBtnSearchClick = () => { @@ -68,6 +79,10 @@ const SearchBarComponent = ({ updateQueryState, currentQueryState }) => { queryString: inputValue, hiddenParams, }); + const id = extractRunIdFromQuery(inputValue, runs); + if (id) { + setActiveRunId(id); + } }; const formatDate = (dateStr) => { @@ -114,7 +129,7 @@ const SearchBarComponent = ({ updateQueryState, currentQueryState }) => { selection placeholder={i18next.t("Select a harvest run...")} options={runOptions} - value={selectedRun?.id || ""} + value={activeRunId || ""} onChange={onRunChange} /> @@ -162,7 +177,7 @@ const SearchBarComponent = ({ updateQueryState, currentQueryState }) => { - +
{i18next.t("Search Logs")}
{ }} /> - + - - + + diff --git a/site/cds_rdm/harvester_download/resources/resource.py b/site/cds_rdm/harvester_download/resources/resource.py index 52f30fbb..f9b37c3b 100644 --- a/site/cds_rdm/harvester_download/resources/resource.py +++ b/site/cds_rdm/harvester_download/resources/resource.py @@ -7,19 +7,19 @@ """Harvester download resource.""" -import re -import uuid from datetime import datetime -from flask import Response, current_app, request -from flask_resources import Resource, route -from invenio_access.permissions import system_identity -from invenio_jobs.models import Run -from invenio_jobs.proxies import current_jobs_logs_service +from flask import Response, request +from flask_resources import HTTPJSONException, Resource, route from cds_rdm.administration.permissions import curators_permission - -INSPIRE_HARVESTER_TASK = "process_inspire" +from cds_rdm.harvester_runs.logs import ( + HarvesterRunError, + fetch_harvester_run_logs, + lines_from_hits, + plain_text_log, + resolve_harvester_run, +) class HarvesterDownloadResource(Resource): @@ -32,124 +32,24 @@ def create_url_rules(self): route("GET", routes["download"], self.download), ] - def download(self): - """Download a harvester run's logs as a plain-text ``.log`` file. - - Mirrors the admin job-run page: status header, failure banner, - truncation warning, and task-grouped entries formatted as - ``[yyyy-MM-dd HH:mm] LEVEL message``. - """ - permission = curators_permission - if not permission.can(): - return {"message": "Permission denied"}, 403 - - run_id = request.args.get("run_id", "").strip() - if not run_id: - return {"message": "Missing run_id"}, 400 - try: - uuid.UUID(run_id) - except ValueError: - return {"message": "Invalid run_id"}, 400 - - run = Run.query.filter_by(id=run_id, parent_run_id=None).one_or_none() - if not run: - return {"message": "Run not found"}, 404 - - if not run.job or run.job.task != INSPIRE_HARVESTER_TASK: - return {"message": "Run is not a harvester run"}, 404 + @staticmethod + def _http_json_error(message, code): + """Create a JSON HTTP error for REST responses.""" + return HTTPJSONException(code=code, description=message) + def download(self): + """Download a harvester run's logs as a plain-text ``.log`` file.""" + if not curators_permission.can(): + raise self._http_json_error("Permission denied", 403) - max_results = current_app.config.get("JOBS_LOGS_MAX_RESULTS", 2000) try: - result = current_jobs_logs_service.search( - system_identity, - params={"q": str(run.id), "sort": "timestamp"}, - ) - hits = list(result.hits) - total = result.total or len(hits) - except Exception: - current_app.logger.exception( - "Failed to fetch structured job logs for harvester run %s", run.id - ) - hits = [] - total = 0 - - def _format_timestamp(raw): - # Admin UI (RunsLogs.js) format. - if not raw: - return "N/A" - try: - return datetime.fromisoformat( - raw.replace("Z", "+00:00") - ).strftime("%Y-%m-%d %H:%M") - except (ValueError, TypeError): - return raw - - # Group by context.task_id in first-seen order (RunsLogs.js buildLogTree). - task_groups = {} - seen = set() - error_count = 0 - warning_count = 0 - for hit in hits: - raw_ts = hit.get("timestamp") - level = hit.get("level", "INFO") - # Collapse whitespace so multi-line errors render on one line - # (admin UI does the same via ``white-space: normal``). - message = re.sub(r"\s+", " ", (hit.get("message") or "")).strip() - key = (raw_ts, level, message) - if key in seen: - continue - seen.add(key) - if level == "ERROR": - error_count += 1 - elif level == "WARNING": - warning_count += 1 - task_id = (hit.get("context") or {}).get("task_id") or "unknown" - task_groups.setdefault(task_id, []).append( - f"[{_format_timestamp(raw_ts)}] {level} {message}" - ) - - lines = [line for group in task_groups.values() for line in group] - - header = [] - status = getattr(run.status, "name", str(run.status)) - header.append(f"Status: {status}") - header.append(f"Started: {_format_timestamp(run.started_at.isoformat())}") - if run.finished_at: - header.append( - f"Finished: {_format_timestamp(run.finished_at.isoformat())}" - ) - - summary = [] - if status in ("FAILED", "PARTIAL_SUCCESS", "SUCCESS"): - summary.append( - { - "FAILED": "Job failed", - "PARTIAL_SUCCESS": "Job partially succeeded", - "SUCCESS": "Job completed successfully", - }[status] - ) - if run.message: - summary.append(run.message) - if error_count: - summary.append(f"{error_count} error(s) found in logs below") - if warning_count: - summary.append(f"{warning_count} warning(s) found in logs below") - if summary: - header.append("") - header.extend(summary) - - if total and total > len(lines): - header.append( - f"Showing first {len(lines)} of {total} log entries " - f"(truncated at JOBS_LOGS_MAX_RESULTS={max_results})." - ) - header.append("=" * 80) - - logs = "\n".join(header + lines) + run = resolve_harvester_run(request.args.get("run_id", "")) + except HarvesterRunError as error: + raise self._http_json_error(error.message, error.code) - if not lines: - logs += "\n" + (run.message or "No logs available for this run.\n") + hits, total = fetch_harvester_run_logs(run) + lines, error_count, warning_count = lines_from_hits(hits) + logs = plain_text_log(run, lines, total, error_count, warning_count) timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") filename = f"harvester_logs_{run.id}_{timestamp}.log" diff --git a/site/cds_rdm/harvester_runs/__init__.py b/site/cds_rdm/harvester_runs/__init__.py new file mode 100644 index 00000000..1e14f47a --- /dev/null +++ b/site/cds_rdm/harvester_runs/__init__.py @@ -0,0 +1,8 @@ +# -*- coding: utf-8 -*- +# +# Copyright (C) 2026 CERN. +# +# CDS-RDM is free software; you can redistribute it and/or modify it +# under the terms of the GPL-2.0 License; see LICENSE file for more details. + +"""Shared helpers for harvester runs.""" diff --git a/site/cds_rdm/harvester_runs/logs.py b/site/cds_rdm/harvester_runs/logs.py new file mode 100644 index 00000000..a49e03a9 --- /dev/null +++ b/site/cds_rdm/harvester_runs/logs.py @@ -0,0 +1,182 @@ +# -*- coding: utf-8 -*- +# +# Copyright (C) 2026 CERN. +# +# CDS-RDM is free software; you can redistribute it and/or modify it +# under the terms of the GPL-2.0 License; see LICENSE file for more details. + +"""Helpers for INSPIRE harvester run logs.""" + +import re +import uuid +from datetime import datetime + +from flask import current_app +from flask_babel import format_datetime +from invenio_access.permissions import system_identity +from invenio_i18n import gettext as _ +from invenio_jobs.models import Run +from invenio_jobs.proxies import current_jobs_logs_service + +INSPIRE_HARVESTER_TASK = "process_inspire" + + +class HarvesterRunError(Exception): + """Error raised when a requested harvester run cannot be used.""" + + def __init__(self, message, code): + """Constructor.""" + self.message = message + self.code = code + super().__init__(message) + + +def format_timestamp(value): + """Format timestamps for display.""" + if value is None or value == "": + return "N/A" + if isinstance(value, datetime): + dt = value + else: + try: + dt = datetime.fromisoformat(str(value).replace("Z", "+00:00")) + except (ValueError, TypeError): + return str(value) + return format_datetime(dt, "yyyy-MM-dd HH:mm") + + +def resolve_harvester_run(run_id): + """Return a top-level INSPIRE harvester run or raise ``HarvesterRunError``.""" + run_id = (run_id or "").strip() + if not run_id: + raise HarvesterRunError("Missing run_id", 400) + try: + uuid.UUID(run_id) + except ValueError: + raise HarvesterRunError("Invalid run_id", 400) + + run = Run.query.filter_by(id=run_id, parent_run_id=None).one_or_none() + if not run: + raise HarvesterRunError("Run not found", 404) + if not run.job or run.job.task != INSPIRE_HARVESTER_TASK: + raise HarvesterRunError("Run is not a harvester run", 404) + return run + + +def fetch_harvester_run_logs(run): + """Return ``(hits, total)`` from structured job logs.""" + try: + result = current_jobs_logs_service.search( + system_identity, + params={ + "q": f'"{run.id}"', + "sort": "timestamp", + }, + ) + hits = list(result.hits) + total = result.total or len(hits) + except Exception: + current_app.logger.exception( + "Failed to fetch structured job logs for harvester run %s", run.id + ) + hits = [] + total = 0 + return hits, total + + +def lines_from_hits(hits): + """Return de-duplicated log lines and severity counts.""" + task_groups = {} + seen = set() + error_count = 0 + warning_count = 0 + for hit in hits: + raw_ts = hit.get("timestamp") + level = hit.get("level", "INFO") + message = re.sub(r"\s+", " ", (hit.get("message") or "")).strip() + key = (raw_ts, level, message) + if key in seen: + continue + seen.add(key) + if level == "ERROR": + error_count += 1 + elif level == "WARNING": + warning_count += 1 + task_id = (hit.get("context") or {}).get("task_id") or "unknown" + task_groups.setdefault(task_id, []).append( + f"[{format_timestamp(raw_ts)}] {level} {message}" + ) + lines = [line for group in task_groups.values() for line in group] + return lines, error_count, warning_count + + +def plain_text_log(run, lines, total, error_count, warning_count): + """Build the plain-text log file content.""" + max_results = current_app.config.get("JOBS_LOGS_MAX_RESULTS", 2000) + status = getattr(run.status, "name", str(run.status)) + header = [ + f"Status: {status}", + f"Started: {format_timestamp(run.started_at)}", + ] + if run.finished_at: + header.append(f"Finished: {format_timestamp(run.finished_at)}") + + summary = [] + if status in ("FAILED", "PARTIAL_SUCCESS", "SUCCESS"): + summary.append( + { + "FAILED": _("Job failed"), + "PARTIAL_SUCCESS": _("Job partially succeeded"), + "SUCCESS": _("Job completed successfully"), + }[status] + ) + if run.message: + summary.append(run.message) + if error_count: + summary.append(_("%(count)s error(s) found in logs below", count=error_count)) + if warning_count: + summary.append( + _("%(count)s warning(s) found in logs below", count=warning_count) + ) + if summary: + header.append("") + header.extend(summary) + + if total and total > len(lines): + header.append( + f"Showing first {len(lines)} of {total} log entries " + f"(truncated at JOBS_LOGS_MAX_RESULTS={max_results})." + ) + header.append("=" * 80) + + logs = "\n".join(header + lines) + if not lines: + logs += "\n" + (run.message or "No logs available for this run.\n") + return logs + + +def report_context(run_id): + """Build context for the colored HTML report page.""" + run = resolve_harvester_run(run_id) + hits, total = fetch_harvester_run_logs(run) + lines, error_count, _unused_warnings = lines_from_hits(hits) + status = getattr(run.status, "name", str(run.status)) + + truncation_message = None + if total and total > len(lines): + truncation_message = ( + f"Log results truncated. Too many log results returned ({total}). " + f"Only the most recent {len(lines)} results are shown." + ) + + display_title = (getattr(run, "title", None) or "").strip() or f"Run {run.id}" + return { + "run": run, + "title": display_title, + "status": status, + "started_at": format_timestamp(run.started_at), + "finished_at": format_timestamp(run.finished_at) if run.finished_at else None, + "truncation_message": truncation_message, + "lines": lines, + "error_count": error_count, + } diff --git a/site/cds_rdm/templates/semantic-ui/cds_rdm/administration/harvester_run_report.html b/site/cds_rdm/templates/semantic-ui/cds_rdm/administration/harvester_run_report.html new file mode 100644 index 00000000..fcf9f298 --- /dev/null +++ b/site/cds_rdm/templates/semantic-ui/cds_rdm/administration/harvester_run_report.html @@ -0,0 +1,30 @@ +{# +Copyright (C) 2026 CERN. + +CDS-RDM is free software; you can redistribute it and/or modify it +under the terms of the GPL-2.0 License; see LICENSE file for more details. + +Job run report: same admin shell as other administration pages (no custom width wrapper). +#} +{% extends "cds_rdm/administration/admin_base_template.html" %} + +{% block page_title %} +{% set back_url = "/administration/harvester-reports?run_id=" ~ run.id %} +
+ + + {{ _("Back") }} + +
+

{{ title }}

+

+ {{ _("Status") }}: {{ status }} + · {{ _("Started") }}: {{ started_at }} + {% if finished_at %}· {{ _("Finished") }}: {{ finished_at }}{% endif %} +

+ +{% endblock page_title %} + +{% block admin_page_content %} +{% include "cds_rdm/harvester_download/report_body.html" %} +{% endblock admin_page_content %} diff --git a/site/cds_rdm/templates/semantic-ui/cds_rdm/harvester_download/report_body.html b/site/cds_rdm/templates/semantic-ui/cds_rdm/harvester_download/report_body.html new file mode 100644 index 00000000..761ba03a --- /dev/null +++ b/site/cds_rdm/templates/semantic-ui/cds_rdm/harvester_download/report_body.html @@ -0,0 +1,91 @@ +{# +Copyright (C) 2026 CERN. + +CDS-RDM is free software; you can redistribute it and/or modify it +under the terms of the GPL-2.0 License; see LICENSE file for more details. + +Job run report body: layout aligned with invenio_jobs RunsLogs. Presentation-only +logic lives here; resource.py only supplies run, lines, and counts. +#} +
+ {% if truncation_message %} +
+ +
+
{{ _("Log results truncated") }}
+

{{ truncation_message }}

+
+
+ {% endif %} + +
+
+

{{ _("Job run") }}

+
+
+ {% if status == "SUCCESS" %} + + {% elif status == "FAILED" %} + + {% elif status == "RUNNING" %} + + {% elif status == "PARTIAL_SUCCESS" %} + + {% elif status == "CANCELLED" %} + + {% elif status == "QUEUED" %} + + {% else %} + + {% endif %} +
+ {% if started_at and started_at != "N/A" %} +

{{ started_at }}

+ {% if run.started_at and run.finished_at %} +

+ {{ ((run.finished_at - run.started_at).total_seconds() // 60) | int }} {{ _("mins") }} +

+ {% endif %} + {% else %} +

{{ _("Not yet started") }}

+ {% endif %} + {% if run.message and status not in ("FAILED", "PARTIAL_SUCCESS") %} +
+ {{ run.message }} +
+ {% endif %} +
+
+
+
+
+ {% if status in ("FAILED", "PARTIAL_SUCCESS") %} +
+ +
+
+ {% if status == "FAILED" %}{{ _("Job failed") }}{% else %}{{ _("Job partially succeeded") }}{% endif %} +
+ {% if run.message %} + 
{{ run.message }}
+ {% endif %} + {% if error_count %} +

{{ _("%(count)s error(s) found in logs below", count=error_count) }}

+ {% endif %} +
+
+ {% endif %} + +
+ {% for line in lines %} +
+ {{ line }} +
+ {% endfor %} + {% if not lines %} +

{{ _("No log lines in this view.") }}

+ {% endif %} +
+
+
+
diff --git a/site/cds_rdm/templates/semantic-ui/invenio_jobs/emails/run_notification.html b/site/cds_rdm/templates/semantic-ui/invenio_jobs/emails/run_notification.html index dcb53f11..d7b2aeea 100644 --- a/site/cds_rdm/templates/semantic-ui/invenio_jobs/emails/run_notification.html +++ b/site/cds_rdm/templates/semantic-ui/invenio_jobs/emails/run_notification.html @@ -32,10 +32,8 @@

Summary

{% endif %} {% if job.task == "process_inspire" %} +{% set harvester_run_id = run.parent_run_id or run.id %} -{% set start_time = run.started_at | string | replace(' ', 'T') %} -{% set end_time = (run.finished_at | string | replace(' ', 'T')) if run.finished_at else '*' %} -{% set timestamp_range = "@timestamp:[" ~ start_time ~ " TO " ~ end_time ~ "]" %}

Harvester Actions

@@ -44,23 +42,23 @@

Harvester Actions

- - Download Harvester Logs + Download error log

- Download all record.publish audit logs from this harvest run + Download the structured job logs for this harvest run

- - View Harvester Reports + View list of changes

- View detailed audit reports for all harvester runs + Open Harvester Reports with this run selected

diff --git a/site/cds_rdm/templates/semantic-ui/invenio_jobs/emails/run_notification.txt b/site/cds_rdm/templates/semantic-ui/invenio_jobs/emails/run_notification.txt index 07f278f8..6150c613 100644 --- a/site/cds_rdm/templates/semantic-ui/invenio_jobs/emails/run_notification.txt +++ b/site/cds_rdm/templates/semantic-ui/invenio_jobs/emails/run_notification.txt @@ -19,17 +19,15 @@ Summary: {% endif %} {% if job.task == "process_inspire" %} +{% set harvester_run_id = run.parent_run_id or run.id %} --- Harvester Actions: -{% set start_time = run.started_at | string | replace(' ', 'T') %} -{% set end_time = (run.finished_at | string | replace(' ', 'T')) if run.finished_at else '*' %} -{% set timestamp_range = "@timestamp:[" ~ start_time ~ " TO " ~ end_time ~ "]" %} -Download Harvester Logs: -{{ config.SITE_UI_URL }}/harvester-reports/download?q={{ timestamp_range | urlencode }}&action=record.publish +Download error log: +{{ config.SITE_UI_URL }}/harvester-reports/download?run_id={{ harvester_run_id }} -View Harvester Reports: -{{ config.SITE_UI_URL }}/administration/harvester-reports?q={{ timestamp_range | urlencode }}&l=list&p=1&s=20&sort=newest +View list of changes: +{{ config.SITE_UI_URL }}/administration/harvester-reports?run_id={{ harvester_run_id }} {% endif %} --- diff --git a/site/cds_rdm/views.py b/site/cds_rdm/views.py index fb931943..76bfbd9a 100644 --- a/site/cds_rdm/views.py +++ b/site/cds_rdm/views.py @@ -45,7 +45,7 @@ def create_cds_clc_sync_bp(app): def create_harvester_download_bp(app): - """Create harvester download blueprint.""" + """Create harvester log download blueprint.""" ext = app.extensions["cds-rdm"] return ext.harvester_download_resource.as_blueprint() @@ -161,5 +161,3 @@ def get_linked_records_search_query(record): final_query = f'({combined_query}) AND is_published:true AND NOT id:"{record_id}"' return final_query - - diff --git a/site/pyproject.toml b/site/pyproject.toml index b4ce4111..40b5afb2 100644 --- a/site/pyproject.toml +++ b/site/pyproject.toml @@ -14,6 +14,7 @@ cds_rdm_rest = "cds_rdm.ext:CDS_RDM_REST" [project.entry-points."invenio_base.blueprints"] cds_rdm_migration = "cds_rdm.legacy.redirector:create_blueprint" harvester_download = "cds_rdm.views:create_harvester_download_bp" +harvester_report = "cds_rdm.administration.harvester_reports:create_harvester_report_blueprint" [project.entry-points."invenio_base.api_blueprints"] clc_sync = "cds_rdm.views:create_cds_clc_sync_bp"