From 689da76d1c759d6368d760b4a1fa942e16095a40 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Wed, 15 Jan 2020 14:13:34 -0800
Subject: ingest: improve tests, support old ingest results

---
 python/fatcat_tools/importers/ingest.py    | 15 ++++++++++++---
 python/tests/files/example_ingest.json     |  2 +-
 python/tests/files/example_ingest.old.json |  1 +
 python/tests/import_ingest.py              | 16 ++++++++++++++++
 4 files changed, 30 insertions(+), 4 deletions(-)
 create mode 100644 python/tests/files/example_ingest.old.json

(limited to 'python')

diff --git a/python/fatcat_tools/importers/ingest.py b/python/fatcat_tools/importers/ingest.py
index 3d391bd8..82a33aaa 100644
--- a/python/fatcat_tools/importers/ingest.py
+++ b/python/fatcat_tools/importers/ingest.py
@@ -112,9 +112,18 @@ class IngestFileResultImporter(EntityImporter):
 
         terminal = row.get('terminal')
         if not terminal:
-            # TODO: support archive.org hits?
-            self.counts['skip-no-terminal'] += 1
-            return None
+            # support old cdx-only ingest results
+            cdx = row.get('cdx')
+            if not cdx:
+                # TODO: support archive.org hits?
+                self.counts['skip-no-terminal'] += 1
+                return None
+            else:
+                terminal = {
+                    'terminal_url': cdx['url'],
+                    'terminal_dt': cdx['datetime'],
+                    'terminal_status_code': cdx.get('status_code') or cdx.get('http_status'),
+                }
 
         # work around old schema
         if not 'terminal_url' in terminal:
diff --git a/python/tests/files/example_ingest.json b/python/tests/files/example_ingest.json
index 005d8742..18804c1b 100644
--- a/python/tests/files/example_ingest.json
+++ b/python/tests/files/example_ingest.json
@@ -1 +1 @@
-{"file_meta": {"sha1hex": "00242a192acc258bdfdb151943419437f440c313", "md5hex": "f4de91152c7ab9fdc2a128f962faebff", "sha256hex": "ffc1005680cb620eec4c913437dfabbf311b535cfe16cbaeb2faec1f92afc362", "size_bytes": 255629, "mimetype": "application/pdf"}, "request": {"project": "unit-tests", "ext_ids": {"doi": "10.123/abc"}}, "cdx": { "datetime": "20170227164644", "url": "http://journals.plos.org/plosmedicine/article/file?id=10.1371/journal.pmed.0020124&type=printable" }, "grobid": {"status_code": 200 } }
+{"file_meta": {"sha1hex": "00242a192acc258bdfdb151943419437f440c313", "md5hex": "f4de91152c7ab9fdc2a128f962faebff", "sha256hex": "ffc1005680cb620eec4c913437dfabbf311b535cfe16cbaeb2faec1f92afc362", "size_bytes": 255629, "mimetype": "application/pdf"}, "request": {"project": "unit-tests", "ext_ids": {"doi": "10.123/abc"}}, "terminal": {"terminal_url": "http://journals.plos.org/plosmedicine/article/file?id=10.1371/journal.pmed.0020124&type=printable", "terminal_dt": "20170227164644", "terminal_sha1hex": "00242a192acc258bdfdb151943419437f440c313"}, "cdx": { "datetime": "20170227164644", "url": "http://journals.plos.org/plosmedicine/article/file?id=10.1371/journal.pmed.0020124&type=printable" }, "grobid": {"status_code": 200 } }
diff --git a/python/tests/files/example_ingest.old.json b/python/tests/files/example_ingest.old.json
new file mode 100644
index 00000000..005d8742
--- /dev/null
+++ b/python/tests/files/example_ingest.old.json
@@ -0,0 +1 @@
+{"file_meta": {"sha1hex": "00242a192acc258bdfdb151943419437f440c313", "md5hex": "f4de91152c7ab9fdc2a128f962faebff", "sha256hex": "ffc1005680cb620eec4c913437dfabbf311b535cfe16cbaeb2faec1f92afc362", "size_bytes": 255629, "mimetype": "application/pdf"}, "request": {"project": "unit-tests", "ext_ids": {"doi": "10.123/abc"}}, "cdx": { "datetime": "20170227164644", "url": "http://journals.plos.org/plosmedicine/article/file?id=10.1371/journal.pmed.0020124&type=printable" }, "grobid": {"status_code": 200 } }
diff --git a/python/tests/import_ingest.py b/python/tests/import_ingest.py
index 7c0a85cd..5089d99e 100644
--- a/python/tests/import_ingest.py
+++ b/python/tests/import_ingest.py
@@ -56,3 +56,19 @@ def test_ingest_dict_parse(ingest_importer):
             if u.rel == "webarchive":
                 assert u.url.startswith("https://web.archive.org/")
         assert len(f.release_ids) == 1
+
+def test_ingest_dict_parse_old(ingest_importer):
+    with open('tests/files/example_ingest.old.json', 'r') as f:
+        raw = json.loads(f.readline())
+        f = ingest_importer.parse_record(raw)
+        assert f.sha1 == "00242a192acc258bdfdb151943419437f440c313"
+        assert f.md5 == "f4de91152c7ab9fdc2a128f962faebff"
+        assert f.mimetype == "application/pdf"
+        assert f.size == 255629
+        assert len(f.urls) == 2
+        for u in f.urls:
+            if u.rel == "web":
+                assert u.url.startswith("http://journals.plos.org")
+            if u.rel == "webarchive":
+                assert u.url.startswith("https://web.archive.org/")
+        assert len(f.release_ids) == 1
-- 
cgit v1.2.3