bibclean: slugs, and whether the one a record has still names it

parity/golden/slug/records.ndjson

@@ -0,0 +1,25 @@
+{"lead_author": "William Zinsser", "proposed": null, "reasons": [], "slug_for": "william-zinsser-on-writing-well-3450", "slugify": "on-writing-well", "tier": null}
+{"lead_author": "Laura Nader", "proposed": "laura-nader-weaponizing-anthropology-3450", "reasons": ["only 0% of slug tokens appear in the current title/author — slug and metadata disagree"], "slug_for": "laura-nader-weaponizing-anthropology-3450", "slugify": "weaponizing-anthropology", "tier": "wrong-book"}
+{"lead_author": "Zinsser, William", "proposed": "zinsser-william-mind-and-brain-1234", "reasons": ["slug opens with placeholder author 'unknown'"], "slug_for": "zinsser-william-mind-and-brain-1234", "slugify": "mind-and-brain", "tier": "placeholder-author"}
+{"lead_author": "Unknown", "proposed": "unknown-mind-and-brain-chaos-and-quantum-mechanics-88", "reasons": ["slug carries a filename or mirror artefact"], "slug_for": "unknown-mind-and-brain-chaos-and-quantum-mechanics-88", "slugify": "mind-and-brain-chaos-and-quantum-mechanics", "tier": "filename-artefact"}
+{"lead_author": "Smith, John", "proposed": "smith-john-the-mill-and-the-valley-99", "reasons": ["slug carries a filename or mirror artefact"], "slug_for": "smith-john-the-mill-and-the-valley-99", "slugify": "the-mill-and-the-valley", "tier": "filename-artefact"}
+{"lead_author": "Microsoft Word", "proposed": "microsoft-word-mat-doc-1", "reasons": ["slug carries a filename or mirror artefact", "recomputes to the same slug: fix the metadata first"], "slug_for": "microsoft-word-mat-doc-1", "slugify": "mat-doc", "tier": "noop-metadata-junk"}
+{"lead_author": "Unknown Author", "proposed": "unknown-author-1234", "reasons": ["slug opens with placeholder author 'unknown'", "new slug is no better: fix the metadata first"], "slug_for": "unknown-author-1234", "slugify": "", "tier": "defer-new-slug-junk"}
+{"lead_author": "Aristotelian Society", "proposed": "aristotelian-society-proceedings-of-the-society-77", "reasons": ["slug opens with placeholder author 'unknown'", "current slug carries a volume marker the new one loses"], "slug_for": "aristotelian-society-proceedings-of-the-society-77", "slugify": "proceedings-of-the-society", "tier": "review-loses-volume"}
+{"lead_author": "the land of iran (Cambridge University Press", "proposed": "the-land-of-iran-cambridge-the-land-of-iran-55", "reasons": ["slug opens with placeholder author 'unknown'", "author field looks like spilled title/series text: 'the land of iran (Cambridge University Press'"], "slug_for": "the-land-of-iran-cambridge-the-land-of-iran-55", "slugify": "the-land-of-iran", "tier": "defer-new-slug-junk"}
+{"lead_author": "Old Testament, Volume II) (Mark Sheridan", "proposed": null, "reasons": [], "slug_for": "old-testament-volume-ii-mark-genesis-12-50-12", "slugify": "genesis-12-50", "tier": null}
+{"lead_author": "A. A. Long", "proposed": null, "reasons": [], "slug_for": "a-a-long-the-cambridge-companion-to-early-greek-philosophy-7", "slugify": "the-cambridge-companion-to-early-greek-philosophy", "tier": null}
+{"lead_author": "()", "proposed": "mind-and-brain-7023", "reasons": ["slug opens with placeholder author 'book'"], "slug_for": "mind-and-brain-7023", "slugify": "mind-and-brain", "tier": "placeholder-author"}
+{"lead_author": "test", "proposed": "test-a-real-book-about-something-8", "reasons": ["slug opens with placeholder author 'test'"], "slug_for": "test-a-real-book-about-something-8", "slugify": "a-real-book-about-something", "tier": "placeholder-author"}
+{"lead_author": "Jaroslav Pelikan", "proposed": null, "reasons": [], "slug_for": "jaroslav-pelikan-christianity-and-classical-culture-the-metamorphosis-of-natural-44", "slugify": "christianity-and-classical-culture-the-metamorphosis-of-natural-theology-in-the-christian-encounter-with-hellenism", "tier": null}
+{"lead_author": "Heidegger, Martin", "proposed": null, "reasons": [], "slug_for": "heidegger-martin-etre-et-temps-9", "slugify": "etre-et-temps", "tier": null}
+{"lead_author": "Θουκυδίδης", "proposed": null, "reasons": [], "slug_for": "thoukudides-athenai-kai-moskha-10", "slugify": "athenai-kai-moskha", "tier": null}
+{"lead_author": "夏目漱石", "proposed": null, "reasons": [], "slug_for": "xia-mu-shu-shi-dong-jing-noshou-zhi-11", "slugify": "dong-jing-noshou-zhi", "tier": null}
+{"lead_author": "Kierkegaard, Søren", "proposed": null, "reasons": [], "slug_for": "kierkegaard-soren-kierkegaard-s-conception-of-god-13", "slugify": "kierkegaard-s-conception-of-god", "tier": null}
+{"lead_author": "Smith, J.", "proposed": null, "reasons": [], "slug_for": "smith-j-12000-years-of-history-14", "slugify": "12000-years-of-history", "tier": null}
+{"lead_author": "Hanna", "proposed": null, "reasons": [], "slug_for": "hanna-tom-jerry-15", "slugify": "tom-jerry", "tier": null}
+{"lead_author": "", "proposed": null, "reasons": [], "slug_for": "an-introduction-to-historical-analysis-16", "slugify": "an-introduction-to-historical-analysis", "tier": null}
+{"lead_author": "Bishop, Christopher M.", "proposed": null, "reasons": [], "slug_for": "bishop-christopher-m-pattern-recognition-and-machine-learning-17", "slugify": "pattern-recognition-and-machine-learning", "tier": null}
+{"lead_author": "Miranda Lundy", "proposed": null, "reasons": [], "slug_for": "miranda-lundy-quadrivium-18", "slugify": "quadrivium", "tier": null}
+{"lead_author": "Smith, John", "proposed": "smith-john-a-book-19", "reasons": ["only 0% of slug tokens appear in the current title/author — slug and metadata disagree"], "slug_for": "smith-john-a-book-19", "slugify": "a-book", "tier": "wrong-book"}
+{"lead_author": "Guardians", "proposed": null, "reasons": [], "slug_for": "guardians-guardians-3190", "slugify": "guardians", "tier": null}