From 94ddfd7167994b4c0f7940317655d152aba302e6 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Thu, 4 Nov 2021 17:08:36 -0700 Subject: short wayback ts: initial cleanup script implementation --- .../fatcat_tools/cleanups/file_short_wayback_ts.py | 251 +++++++++++++++++++++ 1 file changed, 251 insertions(+) create mode 100644 python/fatcat_tools/cleanups/file_short_wayback_ts.py (limited to 'python/fatcat_tools/cleanups/file_short_wayback_ts.py') diff --git a/python/fatcat_tools/cleanups/file_short_wayback_ts.py b/python/fatcat_tools/cleanups/file_short_wayback_ts.py new file mode 100644 index 00000000..2d893dbf --- /dev/null +++ b/python/fatcat_tools/cleanups/file_short_wayback_ts.py @@ -0,0 +1,251 @@ +import argparse +import copy +import os +import sys +from typing import Any, Dict + +import fatcat_openapi_client +from fatcat_openapi_client import ApiClient, FileEntity + +from fatcat_tools import authenticated_api, entity_from_dict, public_api +from fatcat_tools.importers.common import EntityImporter, JsonLinePusher + + +class FileShortWaybackTimestampCleanup(EntityImporter): + """ + This is a one-off / one-time cleanup script for file entities, fix short + timestamps in wayback URLs. These timestamps are supposed to have 14 digits + (datetime with year, hour, seconds, etc). Some legacy file imports ended up + with only 4 or 12 digits. + + While this calls itself a cleanup, it is based on the import code path. It + is not integrated into the `fatcat_import` or `fatcat_cleanup` controller; + instead it has a __main__ function and is invoked like: + + python -m fatcat_tools.cleans.file_short_wayback-ts < blah.json + """ + + def __init__(self, api: ApiClient, **kwargs): + + eg_desc = kwargs.pop("editgroup_description", None) or "Expand short wayback timestamps" + eg_extra = kwargs.pop("editgroup_extra", dict()) + eg_extra["agent"] = eg_extra.get( + "agent", "fatcat_tools.FileShortWaybackTimestampCleanup" + ) + super().__init__( + api, + do_updates=True, + editgroup_description=eg_desc, + editgroup_extra=eg_extra, + **kwargs + ) + self.testing_mode = False + + def want(self, row: Dict[str, Any]) -> bool: + if row["status"].startswith("success"): + return True + else: + self.counts["skip-status"] += 1 + return False + + def parse_record(self, row: Dict[str, Any]) -> FileEntity: + + # bezerk mode doesn't make sense for this importer + assert self.bezerk_mode is False + + fe: FileEntity = entity_from_dict(row["file_entity"], FileEntity) + status: str = row["status"] + assert status.startswith("success") + url_expansions: Dict[str, str] = row["full_urls"] + assert len(url_expansions) >= 1 + + # actual cleanup happens here + any_fixed = False + for fe_url in fe.urls: + if "://web.archive.org/web/" not in fe_url.url: + continue + seq = fe_url.url.split("/") + partial_ts = seq[4] + original_url = "/".join(seq[5:]) + if seq[2] != "web.archive.org": + continue + if len(partial_ts) not in [4, 12]: + continue + if fe_url.url in url_expansions: + fix_url = url_expansions[fe_url.url] + # defensive checks + assert partial_ts in fix_url + assert "://" in fix_url + assert fe_url.url.endswith(original_url) + assert fix_url.endswith(original_url) + fe_url.url = fix_url + any_fixed = True + + if not any_fixed: + self.counts["skip-no-fixes"] += 1 + return None + + # do any other generic file entity cleanups + # this includes removing duplicates + fe = self.generic_file_cleanups(fe) + + # verify that there are no exact duplicates + final_urls = [u.url for u in fe.urls] + assert len(final_urls) == len(list(set(final_urls))) + + return fe + + def try_update(self, fe: FileEntity) -> bool: + + # should always be existing + try: + existing = self.api.get_file(fe.ident) + except fatcat_openapi_client.rest.ApiException as err: + if err.status != 404: + raise err + + if not existing: + self.counts["skip-existing-not-found"] += 1 + return False + + if existing.sha1 != fe.sha1: + self.counts["skip-existing-mismatch"] += 1 + return False + + assert fe.revision and existing.revision + if existing.revision != fe.revision: + self.counts["skip-revision-changed"] += 1 + return False + + # verify that at least one URL remains + if not fe.urls or len(fe.urls) < 1: + self.counts["skip-no-urls"] += 1 + return False + + # verify that all wayback urls have 14-digit timestamps, and are generally well-formed + for u in fe.urls: + if "://web.archive.org/web/" not in u.url: + continue + if u.rel != "webarchive": + self.counts["skip-bad-wayback-rel"] += 1 + return False + seg = u.url.split("/") + if ( + len(seg) < 6 + or seg[0] != "https:" + or seg[2] != "web.archive.org" + or seg[3] != "web" + ): + self.counts["skip-bad-wayback"] += 1 + return False + if len(seg[4]) != 14 or not seg[4].isdigit(): + self.counts["skip-bad-wayback-timestamp"] += 1 + return False + + if existing == fe or existing.urls == fe.urls: + self.counts["skip-no-change"] += 1 + return False + + # not doing a check for "in current editgroup", because the source of + # these corrections (entity dump) contains no dupes + + if not self.testing_mode: + self.api.update_file(self.get_editgroup_id(), existing.ident, existing) + self.counts["update"] += 1 + return False + + +def test_short_wayback_ts() -> None: + api = public_api("http://localhost:9411/v0") + fswtc = FileShortWaybackTimestampCleanup(api=api) + fswtc.testing_mode = True + + assert fswtc.want({"status": "fail"}) is False + assert fswtc.want({"status": "success-self"}) is True + + example_line: Dict[str, Any] = { + "status": "success-db", + "file_entity": { + # note: doesn't match actual entity + "release_ids": ["waldfsctnbcpdbmasgduhaaaaa"], + "mimetype": "application/pdf", + "urls": [ + { + "url": "https://papiro.unizar.es/ojs/index.php/ais/article/download/2187/1971", + "rel": "web", + }, + { + "url": "https://web.archive.org/web/201904301022/https://papiro.unizar.es/ojs/index.php/ais/article/download/2187/1971", + "rel": "webarchive", + }, + ], + "sha256": "0b9e09480ed2e1f08f3c6c72f57ce12b52ea265f580f8810e606b49d64234b29", + "sha1": "be714299b9be21b5afdaa7affd7d710c58269433", + "md5": "9edb542be5b3446a1905e61a8a3abebd", + "size": 666242, + "revision": "fe949be8-7bf9-4c17-be28-8e3e90fb85bd", + "ident": "4ghpvs2t2rdtrdum2mkreh62me", + "state": "active", + }, + "full_urls": { + "https://web.archive.org/web/201904301022/https://papiro.unizar.es/ojs/index.php/ais/article/download/2187/1971": "https://web.archive.org/web/20190430102239/https://papiro.unizar.es/ojs/index.php/ais/article/download/2187/1971" + }, + } + example_fe = entity_from_dict(example_line["file_entity"], FileEntity) + + fe1 = copy.copy(example_fe) + fe1.urls[ + 1 + ].url = "https://web.archive.org/web/20190430102239/https://papiro.unizar.es/ojs/index.php/ais/article/download/2187/1971" + assert fswtc.parse_record(example_line) == fe1 + + # update code path; requires a known file ident and API running locally + assert fswtc.counts["update"] == 0 + dummy_fe = api.get_file("aaaaaaaaaaaaamztaaaaaaaaai") + fe1.ident = dummy_fe.ident + + assert fswtc.try_update(fe1) is False + assert fswtc.counts["skip-existing-mismatch"] == 1 + + fe1.sha1 = dummy_fe.sha1 + assert fswtc.try_update(fe1) is False + assert fswtc.counts["skip-revision-changed"] == 1 + + fe1.revision = dummy_fe.revision + assert fswtc.try_update(fe1) is False + print(fswtc.counts) + assert fswtc.counts["update"] == 1 + + +def main() -> None: + parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter) + parser.add_argument( + "--host-url", default="http://localhost:9411/v0", help="connect to this host/port" + ) + parser.add_argument("--batch-size", help="size of batch to send", default=50, type=int) + parser.set_defaults( + auth_var="FATCAT_API_AUTH_TOKEN", + ) + parser.add_argument( + "json_file", + help="File with jsonlines from file_meta schema to import from", + default=sys.stdin, + type=argparse.FileType("r"), + ) + + args = parser.parse_args() + api = authenticated_api( + args.host_url, + # token is an optional kwarg (can be empty string, None, etc) + token=os.environ.get(args.auth_var), + ) + + fswtc = FileShortWaybackTimestampCleanup( + api, + edit_batch_size=args.batch_size, + ) + JsonLinePusher(fswtc, args.json_file).run() + + +if __name__ == "__main__": + main() -- cgit v1.2.3 From 1ad08edf2d3d06196119ec1eddc932e6423e3e7c Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Thu, 4 Nov 2021 17:56:16 -0700 Subject: wayback short ts: add regression test for dupe URLs --- .../fatcat_tools/cleanups/file_short_wayback_ts.py | 44 ++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'python/fatcat_tools/cleanups/file_short_wayback_ts.py') diff --git a/python/fatcat_tools/cleanups/file_short_wayback_ts.py b/python/fatcat_tools/cleanups/file_short_wayback_ts.py index 2d893dbf..ab1b2a5f 100644 --- a/python/fatcat_tools/cleanups/file_short_wayback_ts.py +++ b/python/fatcat_tools/cleanups/file_short_wayback_ts.py @@ -216,6 +216,50 @@ def test_short_wayback_ts() -> None: print(fswtc.counts) assert fswtc.counts["update"] == 1 + # another example, which failed with an assertion in prod due to duplicated URLs + example_line2: Dict[str, Any] = { + "file_entity": { + "release_ids": ["22jt7euq4fafhblzullmnesso4"], + "mimetype": "application/pdf", + "urls": [ + { + "url": "https://www.jstage.jst.go.jp/article/ibk/59/1/59_KJ00007115297/_pdf", + "rel": "repository", + }, + { + "url": "https://web.archive.org/web/201811010021/https://www.jstage.jst.go.jp/article/ibk/59/1/59_KJ00007115297/_pdf", + "rel": "webarchive", + }, + { + "url": "https://web.archive.org/web/20181101002154/https://www.jstage.jst.go.jp/article/ibk/59/1/59_KJ00007115297/_pdf", + "rel": "webarchive", + }, + ], + "sha256": "51ec58e7a2325d28d1deb0a4bc6422c0e4ae7b12ffb0b6298981a7b8b7730b19", + "sha1": "ad96a584fc6073b9a23736bc61ae0ec4a5661433", + "md5": "3d509743359649e34a27ae70c5cd3018", + "size": 430665, + "extra": { + "shadows": {"scimag_doi": "10.4259/ibk.59.1_194", "scimag_id": "69089904"} + }, + "revision": "f1fa11ff-d521-45cf-9db1-cb3c8bd3ea48", + "ident": "duymhmxk3fgtzk37yp2pvthtxq", + "state": "active", + }, + "full_urls": { + "https://web.archive.org/web/201811010021/https://www.jstage.jst.go.jp/article/ibk/59/1/59_KJ00007115297/_pdf": "https://web.archive.org/web/20181101002154/https://www.jstage.jst.go.jp/article/ibk/59/1/59_KJ00007115297/_pdf" + }, + "status": "success-self", + } + + fe2 = fswtc.parse_record(example_line2) + assert len(fe2.urls) == 2 + assert fe2.urls[0].rel == "repository" + assert ( + fe2.urls[1].url + == "https://web.archive.org/web/20181101002154/https://www.jstage.jst.go.jp/article/ibk/59/1/59_KJ00007115297/_pdf" + ) + def main() -> None: parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter) -- cgit v1.2.3 From 766bc9c6ebe22a29c39c91941f12eed29b85a41d Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Thu, 4 Nov 2021 18:01:49 -0700 Subject: wayback cleanup: actually update entity --- python/fatcat_tools/cleanups/file_short_wayback_ts.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'python/fatcat_tools/cleanups/file_short_wayback_ts.py') diff --git a/python/fatcat_tools/cleanups/file_short_wayback_ts.py b/python/fatcat_tools/cleanups/file_short_wayback_ts.py index ab1b2a5f..d8b8ab9d 100644 --- a/python/fatcat_tools/cleanups/file_short_wayback_ts.py +++ b/python/fatcat_tools/cleanups/file_short_wayback_ts.py @@ -27,7 +27,7 @@ class FileShortWaybackTimestampCleanup(EntityImporter): def __init__(self, api: ApiClient, **kwargs): - eg_desc = kwargs.pop("editgroup_description", None) or "Expand short wayback timestamps" + eg_desc = kwargs.pop("editgroup_description", None) or "Expand trunacted timestamps in wayback URLs" eg_extra = kwargs.pop("editgroup_extra", dict()) eg_extra["agent"] = eg_extra.get( "agent", "fatcat_tools.FileShortWaybackTimestampCleanup" @@ -150,7 +150,9 @@ class FileShortWaybackTimestampCleanup(EntityImporter): # these corrections (entity dump) contains no dupes if not self.testing_mode: - self.api.update_file(self.get_editgroup_id(), existing.ident, existing) + # note: passing 'fe' instead of 'existing' here, which is not + # usually how it goes! + self.api.update_file(self.get_editgroup_id(), fe.ident, fe) self.counts["update"] += 1 return False -- cgit v1.2.3 From 2712b56580c7d5e2e07fdccd990e1918c43880f9 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 5 Nov 2021 11:03:06 -0700 Subject: wayback short ts: another regression test, and some small fmt/tweaks --- .../fatcat_tools/cleanups/file_short_wayback_ts.py | 41 ++++++++++++++++++++-- 1 file changed, 38 insertions(+), 3 deletions(-) (limited to 'python/fatcat_tools/cleanups/file_short_wayback_ts.py') diff --git a/python/fatcat_tools/cleanups/file_short_wayback_ts.py b/python/fatcat_tools/cleanups/file_short_wayback_ts.py index d8b8ab9d..56a5c80e 100644 --- a/python/fatcat_tools/cleanups/file_short_wayback_ts.py +++ b/python/fatcat_tools/cleanups/file_short_wayback_ts.py @@ -27,7 +27,10 @@ class FileShortWaybackTimestampCleanup(EntityImporter): def __init__(self, api: ApiClient, **kwargs): - eg_desc = kwargs.pop("editgroup_description", None) or "Expand trunacted timestamps in wayback URLs" + eg_desc = ( + kwargs.pop("editgroup_description", None) + or "Expand trunacted timestamps in wayback URLs" + ) eg_extra = kwargs.pop("editgroup_extra", dict()) eg_extra["agent"] = eg_extra.get( "agent", "fatcat_tools.FileShortWaybackTimestampCleanup" @@ -37,7 +40,7 @@ class FileShortWaybackTimestampCleanup(EntityImporter): do_updates=True, editgroup_description=eg_desc, editgroup_extra=eg_extra, - **kwargs + **kwargs, ) self.testing_mode = False @@ -74,7 +77,7 @@ class FileShortWaybackTimestampCleanup(EntityImporter): if fe_url.url in url_expansions: fix_url = url_expansions[fe_url.url] # defensive checks - assert partial_ts in fix_url + assert f"/web/{partial_ts}" in fix_url assert "://" in fix_url assert fe_url.url.endswith(original_url) assert fix_url.endswith(original_url) @@ -262,6 +265,38 @@ def test_short_wayback_ts() -> None: == "https://web.archive.org/web/20181101002154/https://www.jstage.jst.go.jp/article/ibk/59/1/59_KJ00007115297/_pdf" ) + # ensure URL order is stable + example_line3: Dict[str, Any] = { + "file_entity": { + "release_ids": ["5rin7f2cdvc5hjkqqw53z7sr3i"], + "mimetype": "application/pdf", + "urls": [ + {"url": "https://pubs.usgs.gov/bul/1108/report.pdf", "rel": "web"}, + { + "url": "https://web.archive.org/web/201904291643/https://pubs.usgs.gov/bul/1108/report.pdf", + "rel": "webarchive", + }, + ], + "sha256": "714cd48c2577e9b058b8f16b4574765da685f67582cc53898a9d6933e45d6cc0", + "sha1": "4efbdb517c0ff3f58136e4efbbec2bd9315400d3", + "md5": "89b6e6cc4e0259317e26ddf1a9a336a0", + "size": 41265, + "revision": "926fcf73-e644-4446-a24b-4d0940a2cf65", + "ident": "lvnz23nzijaapf5iti45zez6zu", + "state": "active", + }, + "full_urls": { + "https://web.archive.org/web/201904291643/https://pubs.usgs.gov/bul/1108/report.pdf": "https://web.archive.org/web/20190429164342/https://pubs.usgs.gov/bul/1108/report.pdf" + }, + "status": "success-db", + } + + fe3 = fswtc.parse_record(example_line3) + assert len(fe3.urls) == 2 + assert fe3.urls[0].rel == "web" + assert fe3.urls[0].url == "https://pubs.usgs.gov/bul/1108/report.pdf" + assert fe3.urls[1].rel == "webarchive" + def main() -> None: parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter) -- cgit v1.2.3 From 86e6850e70617e1609b79e0ee4bfe2a26f7f992e Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 9 Nov 2021 14:17:31 -0800 Subject: cleanups: tweaks to wayback CDX cleanup scripts --- notes/cleanups/scripts/fetch_full_cdx_ts.py | 9 ++++++++- python/fatcat_tools/cleanups/file_short_wayback_ts.py | 18 +++++++++++++----- 2 files changed, 21 insertions(+), 6 deletions(-) (limited to 'python/fatcat_tools/cleanups/file_short_wayback_ts.py') diff --git a/notes/cleanups/scripts/fetch_full_cdx_ts.py b/notes/cleanups/scripts/fetch_full_cdx_ts.py index 6c6817ab..6f67c7e1 100644 --- a/notes/cleanups/scripts/fetch_full_cdx_ts.py +++ b/notes/cleanups/scripts/fetch_full_cdx_ts.py @@ -157,7 +157,14 @@ def process_file(fe, session) -> dict: if short in full_urls: continue - cdx_record = get_api_cdx(original_url, partial_dt=ts, http_session=session) + cdx_record = None + try: + cdx_record = get_api_cdx(original_url, partial_dt=ts, http_session=session) + except requests.exceptions.HTTPError as e: + if e.response.status_code == 403: + return dict(file_entity=fe, full_urls=full_urls, status="fail-cdx-403") + else: + raise if cdx_record: if cdx_record['sha1hex'] == fe['sha1'] and cdx_record['url'] == original_url and cdx_record['datetime'].startswith(ts): assert len(cdx_record['datetime']) == 14 and cdx_record['datetime'].isdigit() diff --git a/python/fatcat_tools/cleanups/file_short_wayback_ts.py b/python/fatcat_tools/cleanups/file_short_wayback_ts.py index 56a5c80e..a9b19921 100644 --- a/python/fatcat_tools/cleanups/file_short_wayback_ts.py +++ b/python/fatcat_tools/cleanups/file_short_wayback_ts.py @@ -22,7 +22,7 @@ class FileShortWaybackTimestampCleanup(EntityImporter): is not integrated into the `fatcat_import` or `fatcat_cleanup` controller; instead it has a __main__ function and is invoked like: - python -m fatcat_tools.cleans.file_short_wayback-ts < blah.json + python -m fatcat_tools.cleans.file_short_wayback_ts - < blah.json """ def __init__(self, api: ApiClient, **kwargs): @@ -77,10 +77,18 @@ class FileShortWaybackTimestampCleanup(EntityImporter): if fe_url.url in url_expansions: fix_url = url_expansions[fe_url.url] # defensive checks - assert f"/web/{partial_ts}" in fix_url + if not ( + f"/web/{partial_ts}" in fix_url + and fe_url.url.endswith(original_url) + and fix_url.endswith(original_url) + ): + print( + f"bad replacement URL: partial_ts={partial_ts} original={original_url} fix_url={fix_url}", + file=sys.stderr, + ) + self.counts["skip-bad-replacement"] += 1 + return None assert "://" in fix_url - assert fe_url.url.endswith(original_url) - assert fix_url.endswith(original_url) fe_url.url = fix_url any_fixed = True @@ -305,7 +313,7 @@ def main() -> None: ) parser.add_argument("--batch-size", help="size of batch to send", default=50, type=int) parser.set_defaults( - auth_var="FATCAT_API_AUTH_TOKEN", + auth_var="FATCAT_AUTH_WORKER_CLEANUP", ) parser.add_argument( "json_file", -- cgit v1.2.3 From 996b2e2084c1798126bd91dd950c063982398bec Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 9 Nov 2021 15:46:20 -0800 Subject: more iteration on short wayback timestamp cleanup --- notes/cleanups/scripts/fetch_full_cdx_ts.py | 2 +- notes/cleanups/wayback_timestamps.md | 129 ++++++++++++++++++++- .../fatcat_tools/cleanups/file_short_wayback_ts.py | 2 +- 3 files changed, 129 insertions(+), 4 deletions(-) (limited to 'python/fatcat_tools/cleanups/file_short_wayback_ts.py') diff --git a/notes/cleanups/scripts/fetch_full_cdx_ts.py b/notes/cleanups/scripts/fetch_full_cdx_ts.py index 6f67c7e1..d5b0c476 100644 --- a/notes/cleanups/scripts/fetch_full_cdx_ts.py +++ b/notes/cleanups/scripts/fetch_full_cdx_ts.py @@ -137,7 +137,7 @@ def process_file(fe, session) -> dict: if short in full_urls: continue - if original_url in self_urls: + if original_url in self_urls and ts in self_urls[original_url]: full_urls[short] = self_urls[original_url] status = "success-self" continue diff --git a/notes/cleanups/wayback_timestamps.md b/notes/cleanups/wayback_timestamps.md index 81785992..85e5f94f 100644 --- a/notes/cleanups/wayback_timestamps.md +++ b/notes/cleanups/wayback_timestamps.md @@ -61,9 +61,10 @@ Yes, 4-digit is a popular pattern as well, need to handle those: # 111M 0:13:22 [ 139k/s] zcat files_20211007_moreshortts.json.gz | wc -l + # 9,958,854 zcat files_20211007_moreshortts.json.gz | shuf -n10000 > files_20211007_moreshortts.10k_sample.json - # 9,958,854 + ## Fetch Complete URL @@ -114,6 +115,14 @@ Again with the broader set: 6175 "success-db" 3035 "success-self" +While running a larger batch, got a CDX API error: + + requests.exceptions.HTTPError: 403 Client Error: Forbidden for url: https://web.archive.org/cdx/search/cdx?url=https%3A%2F%2Fwww.psychologytoday.com%2Ffiles%2Fu47%2FHenry_et_al.pdf&from=2017&to=2017&matchType=exact&output=json&limit=20 + + org.archive.util.io.RuntimeIOException: org.archive.wayback.exception.AdministrativeAccessControlException: Blocked Site Error + +So maybe need to use credentials after all. + ## Cleanup Process @@ -128,11 +137,13 @@ It looks like the rel swap is already implemented in `generic_file_cleanups()`. From sampling it seems like the mimetype issue is pretty small, so not going to bite that off now. The "bogus file" issue requires thought, so also skipping. -## Commands + +## Commands (old) Running with 8x parallelism to not break things; expecting some errors along the way, may need to add handlers for connection errors etc: + # OLD SNAPSHOT zcat files_20211007_moreshortts.json.gz \ | parallel -j8 --linebuffer --round-robin --pipe ./fetch_full_cdx_ts.py \ | pv -l \ @@ -140,3 +151,117 @@ the way, may need to add handlers for connection errors etc: > files_20211007_moreshortts.fetched.json.gz At 300 records/sec, this should take around 9-10 hours to process. + + + +## Prep Again (2021-11-09) + +After fixing "sort" issue and re-dumping file entities (2021-11-05 snapshot). + +Filter again: + + # note: in the future use pigz instead of gzip here + zcat file_export.json.gz \ + | pv -l \ + | rg 'web.archive.org/web/\d{4,12}/' \ + | gzip \ + > files_20211105_moreshortts.json.gz + # 112M 0:13:27 [ 138k/s] + + zcat files_20211105_moreshortts.json.gz | wc -l + # 9,958,854 + # good, exact same number as previous snapshot + + zcat files_20211105_moreshortts.json.gz | shuf -n10000 > files_20211105_moreshortts.10k_sample.json + # done + + cat files_20211105_moreshortts.10k_sample.json \ + | ./fetch_full_cdx_ts.py \ + | pv -l \ + > files_20211105_moreshortts.10k_sample.fetched.json + # 10.0k 0:03:36 [46.3 /s] + + cat files_20211105_moreshortts.10k_sample.fetched.json | jq .status | sort | uniq -c + 13 "fail-not-found" + 774 "success-api" + 6193 "success-db" + 3020 "success-self" + +After tweaking `success-self` logic: + + 13 "fail-not-found" + 859 "success-api" + 6229 "success-db" + 2899 "success-self" + + +## Testing in QA + +Copied `sample_out.json` to fatcat QA instance and renamed as `files_20211007_moreshortts.10k_sample.fetched.json` + + # OLD ATTEMPT + export FATCAT_API_AUTH_TOKEN=[...] + head -n10 /srv/fatcat/datasets/files_20211007_moreshortts.10k_sample.fetched.json \ + | python -m fatcat_tools.cleanups.file_short_wayback_ts - + +Ran in to issues, iterated above. + +Trying again with updated script and sample file: + + export FATCAT_AUTH_WORKER_CLEANUP=[...] + + head -n10 /srv/fatcat/datasets/files_20211105_moreshortts.10k_sample.fetched.json \ + | python -m fatcat_tools.cleanups.file_short_wayback_ts - + # Counter({'total': 10, 'update': 10, 'skip': 0, 'insert': 0, 'exists': 0}) + +Manually inspected and these look good. Trying some repeats and larger batched: + + head -n10 /srv/fatcat/datasets/files_20211105_moreshortts.10k_sample.fetched.json \ + | python -m fatcat_tools.cleanups.file_short_wayback_ts - + # Counter({'total': 10, 'skip-revision-changed': 10, 'skip': 0, 'insert': 0, 'update': 0, 'exists': 0}) + + head -n1000 /srv/fatcat/datasets/files_20211105_moreshortts.10k_sample.fetched.json \ + | python -m fatcat_tools.cleanups.file_short_wayback_ts - + + [...] + bad replacement URL: partial_ts=201807271139 original=http://www.scielo.br/pdf/qn/v20n1/4918.pdf fix_url=https://web.archive.org/web/20170819080342/http://www.scielo.br/pdf/qn/v20n1/4918.pdf + bad replacement URL: partial_ts=201904270207 original=https://www.matec-conferences.org/articles/matecconf/pdf/2018/62/matecconf_iccoee2018_03008.pdf fix_url=https://web.archive.org/web/20190501060839/https://www.matec-conferences.org/articles/matecconf/pdf/2018/62/matecconf_iccoee2018_03008.pdf + bad replacement URL: partial_ts=201905011445 original=https://cdn.intechopen.com/pdfs/5886.pdf fix_url=https://web.archive.org/web/20190502203832/https://cdn.intechopen.com/pdfs/5886.pdf + [...] + + # Counter({'total': 1000, 'update': 969, 'skip': 19, 'skip-bad-replacement': 18, 'skip-revision-changed': 10, 'skip-bad-wayback-timestamp': 2, 'skip-status': 1, 'insert': 0, 'exists': 0}) + + +It looks like these "bad replacement URLs" are due to timestamp mismatches. Eg, the partial timestamp is not part of the final timestamp. + +Tweaked fetch script and re-ran: + + # Counter({'total': 1000, 'skip-revision-changed': 979, 'update': 18, 'skip-bad-wayback-timestamp': 2, 'skip': 1, 'skip-status': 1, 'insert': 0, 'exists': 0}) + +Cool. Sort of curious what the deal is with those `skip-bad-wayback-timestamp`. + +Run the rest through: + + cat /srv/fatcat/datasets/files_20211105_moreshortts.10k_sample.fetched.json \ + | python -m fatcat_tools.cleanups.file_short_wayback_ts - + # Counter({'total': 10000, 'update': 8976, 'skip-revision-changed': 997, 'skip-bad-wayback-timestamp': 14, 'skip': 13, 'skip-status': 13, 'insert': 0, 'exists': 0}) + +Should tweak batch size to 100 (vs. 50). + +How to parallelize import: + + # from within pipenv + cat /srv/fatcat/datasets/files_20211105_moreshortts.10k_sample.fetched.json \ + | parallel -j8 --linebuffer --round-robin --pipe python -m fatcat_tools.cleanups.file_short_wayback_ts - + + +## Full Batch Commands + +Running in bulk again: + + zcat files_20211105_moreshortts.json.gz \ + | parallel -j8 --linebuffer --round-robin --pipe ./fetch_full_cdx_ts.py \ + | pv -l \ + | gzip \ + > files_20211105_moreshortts.fetched.json.gz + diff --git a/python/fatcat_tools/cleanups/file_short_wayback_ts.py b/python/fatcat_tools/cleanups/file_short_wayback_ts.py index a9b19921..e2595912 100644 --- a/python/fatcat_tools/cleanups/file_short_wayback_ts.py +++ b/python/fatcat_tools/cleanups/file_short_wayback_ts.py @@ -311,7 +311,7 @@ def main() -> None: parser.add_argument( "--host-url", default="http://localhost:9411/v0", help="connect to this host/port" ) - parser.add_argument("--batch-size", help="size of batch to send", default=50, type=int) + parser.add_argument("--batch-size", help="size of batch to send", default=100, type=int) parser.set_defaults( auth_var="FATCAT_AUTH_WORKER_CLEANUP", ) -- cgit v1.2.3 From fd0cf6b55567e3081b9e57e2423d6d0e529ace41 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 9 Nov 2021 19:46:55 -0800 Subject: cleanups: add more state=active checks --- python/fatcat_tools/cleanups/file_release_bugfix.py | 4 ++++ python/fatcat_tools/cleanups/file_short_wayback_ts.py | 4 ++++ 2 files changed, 8 insertions(+) (limited to 'python/fatcat_tools/cleanups/file_short_wayback_ts.py') diff --git a/python/fatcat_tools/cleanups/file_release_bugfix.py b/python/fatcat_tools/cleanups/file_release_bugfix.py index 6eb60205..5ac69d1a 100644 --- a/python/fatcat_tools/cleanups/file_release_bugfix.py +++ b/python/fatcat_tools/cleanups/file_release_bugfix.py @@ -131,6 +131,10 @@ class FileReleaseBugfix(EntityImporter): self.counts["skip-existing-not-found"] += 1 return False + if existing.state != "active": + self.counts["skip-existing-entity-state"] += 1 + return False + if wrong_release_ident not in existing.release_ids: self.counts["skip-existing-fixed"] += 1 return False diff --git a/python/fatcat_tools/cleanups/file_short_wayback_ts.py b/python/fatcat_tools/cleanups/file_short_wayback_ts.py index e2595912..bdd49f9b 100644 --- a/python/fatcat_tools/cleanups/file_short_wayback_ts.py +++ b/python/fatcat_tools/cleanups/file_short_wayback_ts.py @@ -119,6 +119,10 @@ class FileShortWaybackTimestampCleanup(EntityImporter): self.counts["skip-existing-not-found"] += 1 return False + if existing.state != "active": + self.counts["skip-existing-entity-state"] += 1 + return False + if existing.sha1 != fe.sha1: self.counts["skip-existing-mismatch"] += 1 return False -- cgit v1.2.3