diff options
| author | Bryan Newbold <bnewbold@robocracy.org> | 2021-10-18 10:17:54 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@robocracy.org> | 2021-10-18 10:17:54 -0700 |
| commit | 6184ecca3a2e072c11482020938566dc8841bf52 (patch) | |
| tree | 851f51a37edaf6d09d9af3492393f36c71a332c9 /python | |
| parent | cdeee1f92ec4b1fdcc439fc5d975c175c162bfe2 (diff) | |
| download | fatcat-6184ecca3a2e072c11482020938566dc8841bf52.tar.gz fatcat-6184ecca3a2e072c11482020938566dc8841bf52.zip | |
WIP: more fileset ingest
Diffstat (limited to 'python')
| -rw-r--r-- | python/fatcat_tools/importers/ingest.py | 34 |
1 files changed, 21 insertions, 13 deletions
diff --git a/python/fatcat_tools/importers/ingest.py b/python/fatcat_tools/importers/ingest.py index 301be3ef..288c4cff 100644 --- a/python/fatcat_tools/importers/ingest.py +++ b/python/fatcat_tools/importers/ingest.py @@ -64,6 +64,9 @@ class IngestFileResultImporter(EntityImporter): "application/jats+xml", "application/tei+xml", "text/xml"): self.counts['skip-mimetype'] += 1 return False + elif row['request'].get('ingest_type') in ['component', 'src', 'dataset-file']: + # we rely on sandcrawler for these checks + pass else: self.counts['skip-ingest-type'] += 1 return False @@ -599,6 +602,10 @@ class IngestFilesetResultImporter(IngestFileResultImporter): self.counts['skip-empty-manifest'] += 1 return False + if len(row.get('manifest')) == 1: + self.counts['skip-single-file'] += 1 + return False + if len(row.get('manifest')) > self.max_file_count: self.counts['skip-too-many-files'] += 1 return False @@ -621,34 +628,35 @@ class IngestFilesetResultImporter(IngestFileResultImporter): return True def parse_fileset_urls(self, row): - # XXX: create URLs and rel for dataset ingest if not row.get('strategy'): return [] + strategy = row['strategy'] urls = [] - if row['strategy'] == 'archiveorg-fileset' and row.get('archiveorg_item_name'): + if strategy == 'archiveorg-fileset' and row.get('archiveorg_item_name'): urls.append(fatcat_openapi_client.FilesetUrl( url=f"https://archive.org/download/{row['archiveorg_item_name']}/", rel="archive-base", )) - elif row['strategy'] == 'archiveorg-fileset-bundle' and row.get('archiveorg_item_name'): - # XXX: what is the filename of bundle? + if row['strategy'].startswith('web-') and row.get('platform_base_url'): urls.append(fatcat_openapi_client.FilesetUrl( - url=f"https://archive.org/download/{row['archiveorg_item_name']}/", - rel="archive-bundle", + url=f"https://web.archive.org/web/{row['web_base_url_dt']}/{row['web_base_url']}", + rel="webarchive-base", )) - elif row['strategy'].startswith('web') and row.get('platform_base_url'): + # TODO: repository-base + # TODO: web-base + + if row['strategy'] == 'archiveorg-fileset-bundle' and row.get('archiveorg_item_name'): + # TODO: bundle path urls.append(fatcat_openapi_client.FilesetUrl( - url=f"https://web.archive.org/web/{row['web_base_url_dt']}/{row['web_base_url']}", - rel="webarchive", + url=f"https://archive.org/download/{row['archiveorg_item_name']}/{bundle_path}", + rel="archive-bundle", )) - elif row['strategy'] == 'web-fileset-bundle' and row.get('platform_bundle_url'): + + if row['strategy'] == 'web-fileset-bundle' and row.get('platform_bundle_url'): urls.append(fatcat_openapi_client.FilesetUrl( url=f"https://web.archive.org/web/{row['web_bundle_url_dt']}/{row['web_bundle_url']}", rel="webarchive-bundle", )) - else: - # if no archival URLs, bail out - return [] # add any additional / platform URLs here if row.get('platform_bundle_url'): |