From 09b737d1182837635856dfa2fcc4c384dfd58aaf Mon Sep 17 00:00:00 2001 From: Martin Czygan Date: Sat, 12 Dec 2020 02:21:59 +0100 Subject: get rid of 'ok' and 'miss' --- fuzzycat/common.py | 98 +++++++++--------- fuzzycat/verify.py | 104 +++++++++---------- tests/data/verify.csv | 276 +++++++++++++++++++++++++------------------------- 3 files changed, 238 insertions(+), 240 deletions(-) diff --git a/fuzzycat/common.py b/fuzzycat/common.py index 2bb25c6..9ee1239 100644 --- a/fuzzycat/common.py +++ b/fuzzycat/common.py @@ -3,7 +3,8 @@ from enum import Enum class Status(str, Enum): """ - Match status. + Match status. The match status "TODO" is a placeholder, e.g. to trigger a + test failure. """ AMBIGUOUS = 'ambiguous' DIFFERENT = 'different' @@ -13,54 +14,51 @@ class Status(str, Enum): TODO = 'todo' -class OK(str, Enum): +class Reason(str, Enum): """ - Reason for assuming we have a match. + Reason for assuming we have a match or miss. No hard rules on naming. """ - ARXIV_VERSION = 'ok.arxiv_version' - CUSTOM_BSI_SUBDOC = 'ok.custom_bsi_subdoc' - CUSTOM_BSI_UNDATED = 'ok.custom_bsi_undated' - CUSTOM_IEEE_ARXIV = 'ok.custom_ieee_arxiv' - DATACITE_RELATED_ID = 'ok.datacite_related_id' - DATACITE_VERSION = 'ok.datacite_version' - DOI = 'ok.doi' - DUMMY = 'ok.dummy' - FIGSHARE_VERSION = 'ok.figshare_version' - JACCARD_AUTHORS = 'ok.jaccard_authors' - PMID_DOI_PAIR = 'ok.pmid_doi_pair' - PREPRINT_PUBLISHED = 'ok.preprint_published' - SLUG_TITLE_AUTHOR_MATCH = 'ok.slug_title_author_match' - TITLE_AUTHOR_MATCH = 'ok.title_author_match' - TOKENIZED_AUTHORS = 'ok.tokenized_authors' - VERSIONED_DOI = 'ok.versioned_doi' - WORK_ID = 'ok.work_id' - - -class Miss(str, Enum): - """ - Reasons indicating mismatch. - """ - APPENDIX = 'miss.appendix' - ARXIV_VERSION = 'miss.arxiv_version' - BLACKLISTED = 'miss.blacklisted' - BLACKLISTED_FRAGMENT = 'miss.blacklisted_fragment' - BOOK_CHAPTER = 'miss.book_chapter' - CHEM_FORMULA = 'miss.chem_formula' - COMPONENT = 'miss.component' - CONTAINER = 'miss.container' - CONTRIB_INTERSECTION_EMPTY = 'miss.contrib_intersection_empty' - CUSTOM_IOP_MA_PATTERN = 'miss.custom_iop_ma_pattern' - CUSTOM_PREFIX_10_14288 = 'miss.custom_prefix_10_14288' - CUSTOM_PREFIX_10_5860_CHOICE_REVIEW = 'miss.custom_prefix_10_5860_choice_review' - CUSTOM_PREFIX_10_7916 = 'miss.custom_prefix_10_7916' - CUSTOM_VHS = 'miss.vhs' # https://fatcat.wiki/release/44gk5ben5vghljq6twm7lwmxla - DATASET_DOI = 'miss.dataset_doi' - JSTOR_ID = 'miss.jstor_id' - NUM_DIFF = 'miss.num_diff' - PAGE_COUNT = 'miss.page_count' - RELEASE_TYPE = 'miss.release_type' - SHARED_DOI_PREFIX = 'miss.shared_doi_prefix' - SHORT_TITLE = 'miss.short_title' - SUBTITLE = 'miss.subtitle' - TITLE_FILENAME = 'miss.title_filename' - YEAR = 'miss.year' + APPENDIX = 'appendix' + ARXIV_VERSION = 'arxiv_version' + BLACKLISTED = 'blacklisted' + BLACKLISTED_FRAGMENT = 'blacklisted_fragment' + BOOK_CHAPTER = 'book_chapter' + CHEM_FORMULA = 'chem_formula' + COMPONENT = 'component' + CONTAINER = 'container' + CONTAINER_NAME_BLACKLIST = 'container_name_blacklist' + CONTRIB_INTERSECTION_EMPTY = 'contrib_intersection_empty' + CUSTOM_BSI_SUBDOC = 'custom_bsi_subdoc' + CUSTOM_BSI_UNDATED = 'custom_bsi_undated' + CUSTOM_IEEE_ARXIV = 'custom_ieee_arxiv' + CUSTOM_IOP_MA_PATTERN = 'custom_iop_ma_pattern' + CUSTOM_PREFIX_10_14288 = 'custom_prefix_10_14288' + CUSTOM_PREFIX_10_5860_CHOICE_REVIEW = 'custom_prefix_10_5860_choice_review' + CUSTOM_PREFIX_10_7916 = 'custom_prefix_10_7916' + CUSTOM_VHS = 'vhs' # https://fatcat.wiki/release/44gk5ben5vghljq6twm7lwmxla + DATACITE_RELATED_ID = 'datacite_related_id' + DATACITE_VERSION = 'datacite_version' + DATASET_DOI = 'dataset_doi' + DOI = 'doi' + DUMMY = 'dummy' + FIGSHARE_VERSION = 'figshare_version' + JACCARD_AUTHORS = 'jaccard_authors' + JSTOR_ID = 'jstor_id' + MAX_CLUSTER_SIZE_EXCEEDED = 'max_cluster_size_exceeded' + NUM_DIFF = 'num_diff' + PAGE_COUNT = 'page_count' + PMID_DOI_PAIR = 'pmid_doi_pair' + PREPRINT_PUBLISHED = 'preprint_published' + PUBLISHER_BLACKLIST = 'publisher_blacklist' + RELEASE_TYPE = 'release_type' + SHARED_DOI_PREFIX = 'shared_doi_prefix' + SHORT_TITLE = 'short_title' + SINGULAR_CLUSTER = 'singular_cluster' + SLUG_TITLE_AUTHOR_MATCH = 'slug_title_author_match' + SUBTITLE = 'subtitle' + TITLE_AUTHOR_MATCH = 'title_author_match' + TITLE_FILENAME = 'title_filename' + TOKENIZED_AUTHORS = 'tokenized_authors' + VERSIONED_DOI = 'versioned_doi' + WORK_ID = 'work_id' + YEAR = 'year' diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py index 94e8327..973ea13 100644 --- a/fuzzycat/verify.py +++ b/fuzzycat/verify.py @@ -74,7 +74,7 @@ import sys from glom import PathAccessError, glom -from fuzzycat.common import OK, Miss, Status +from fuzzycat.common import Status, Reason from fuzzycat.data import (CONTAINER_NAME_BLACKLIST, PUBLISHER_BLACKLIST, TITLE_BLACKLIST, TITLE_FRAGMENT_BLACKLIST) from fuzzycat.utils import (author_similarity_score, contains_chemical_formula, dict_key_exists, @@ -115,19 +115,19 @@ class GroupVerifier: doc = json.loads(line) k, vs = get_key_values(doc) if len(vs) < 2: - self.counter["skip.unique"] += 1 + self.counter[Reason.SINGULAR_CLUSTER] += 1 continue if len(vs) > self.max_cluster_size: - self.counter["skip.too_large"] += 1 + self.counter[Reason.MAX_CLUSTER_SIZE_EXCEEDED] += 1 continue for a, b in itertools.combinations(vs, r=2): for re in (a, b): container_name = re.get("extra", {}).get("container_name", "") or "" if container_name.lower().strip() in CONTAINER_NAME_BLACKLIST: - self.counter["skip.container_name_blacklist"] += 1 + self.counter[Reason.CONTAINER_NAME_BLACKLIST] += 1 continue if re.get("publisher", "").lower().strip() in PUBLISHER_BLACKLIST: - self.counter["skip.publisher_blacklist"] += 1 + self.counter[Reason.PUBLISHER_BLACKLIST] += 1 continue result, reason = verify(a, b) self.counter[reason] += 1 @@ -146,12 +146,12 @@ def verify(a, b): """ try: if glom(a, "ext_ids.doi") == glom(b, "ext_ids.doi"): - return (Status.EXACT, OK.DOI) + return (Status.EXACT, Reason.DOI) except PathAccessError: pass if a.get("work_id") and a.get("work_id") == b.get("work_id"): - return (Status.EXACT, OK.WORK_ID) + return (Status.EXACT, Reason.WORK_ID) a_title = a.get("title", "") a_title_lower = a_title.lower() @@ -159,27 +159,27 @@ def verify(a, b): b_title_lower = b_title.lower() if len(a_title) < 5: - return (Status.AMBIGUOUS, Miss.SHORT_TITLE) + return (Status.AMBIGUOUS, Reason.SHORT_TITLE) if a_title_lower in TITLE_BLACKLIST: - return (Status.AMBIGUOUS, Miss.BLACKLISTED) + return (Status.AMBIGUOUS, Reason.BLACKLISTED) for fragment in TITLE_FRAGMENT_BLACKLIST: if fragment in a_title_lower: - return (Status.AMBIGUOUS, Miss.BLACKLISTED_FRAGMENT) + return (Status.AMBIGUOUS, Reason.BLACKLISTED_FRAGMENT) # https://fatcat.wiki/release/rnso2swxzvfonemgzrth3arumi, # https://fatcat.wiki/release/caxa7qbfqvg3bkgz4nwvapgnvi if "subject index" in a_title_lower and "subject index" in b_title_lower: try: if glom(a, "container_id") != glom(b, "container_id"): - return (Status.DIFFERENT, Miss.CONTAINER) + return (Status.DIFFERENT, Reason.CONTAINER) except PathAccessError: pass try: if a_title and a_title == b_title and glom(a, "extra.datacite.metadataVersion") != glom( b, "extra.datacite.metadataVersion"): - return (Status.EXACT, OK.DATACITE_VERSION) + return (Status.EXACT, Reason.DATACITE_VERSION) except PathAccessError: pass @@ -191,7 +191,7 @@ def verify(a, b): # https://fatcat.wiki/release/63g4ukdxajcqhdytqla6du3t3u, # https://fatcat.wiki/release/rz72bzfevzeofdeb342c6z45qu; # https://api.datacite.org/application/vnd.datacite.datacite+json/10.14288/1.0011045 - return (Status.DIFFERENT, Miss.CUSTOM_PREFIX_10_14288) + return (Status.DIFFERENT, Reason.CUSTOM_PREFIX_10_14288) except PathAccessError: pass @@ -200,7 +200,7 @@ def verify(a, b): b_doi = glom(b, "ext_ids.doi") if has_doi_prefix(a_doi, "10.3403") and has_doi_prefix(b_doi, "10.3403"): if a_doi + "u" == b_doi or b_doi + "u" == a_doi: - return (Status.STRONG, OK.CUSTOM_BSI_UNDATED) + return (Status.STRONG, Reason.CUSTOM_BSI_UNDATED) # Reference to subdocument. # https://api.fatcat.wiki/v0/release/tcro5wr6brhqnf5wettyiauw34 # https://api.fatcat.wiki/v0/release/s7a4o5v5gfg4tbzna6poyg7nzy @@ -208,7 +208,7 @@ def verify(a, b): and not dict_key_exists(b, "extra.subtitle")) or (dict_key_exists(b, "extra.subtitle") and not dict_key_exists(a, "extra.subtitle"))): - return (Status.STRONG, OK.CUSTOM_BSI_SUBDOC) + return (Status.STRONG, Reason.CUSTOM_BSI_SUBDOC) except PathAccessError: pass @@ -218,15 +218,15 @@ def verify(a, b): if has_doi_prefix(a_doi, "10.1149") and has_doi_prefix(b_doi, "10.1149"): if (a_doi.startswith("10.1149/ma") and not b_doi.startswith("10.1149/ma") or b_doi.startswith("10.1149/ma") and not a_doi.startswith("10.1149/ma")): - return (Status.DIFFERENT, Miss.CUSTOM_IOP_MA_PATTERN) + return (Status.DIFFERENT, Reason.CUSTOM_IOP_MA_PATTERN) except PathAccessError: pass if "Zweckverband Volkshochschule " in a_title and a_title != b_title: - return (Status.DIFFERENT, Miss.CUSTOM_VHS) + return (Status.DIFFERENT, Reason.CUSTOM_VHS) if re.match(r"appendix ?[^ ]*$", a_title_lower): - return (Status.AMBIGUOUS, Miss.APPENDIX) + return (Status.AMBIGUOUS, Reason.APPENDIX) try: # TODO: figshare versions, "xxx.v1" @@ -236,7 +236,7 @@ def verify(a, b): a_doi_v_stripped = re.sub(r"[.]v[0-9]+$", "", glom(a, "ext_ids.doi")) b_doi_v_stripped = re.sub(r"[.]v[0-9]+$", "", glom(b, "ext_ids.doi")) if a_doi_v_stripped == b_doi_v_stripped: - return (Status.STRONG, OK.FIGSHARE_VERSION) + return (Status.STRONG, Reason.FIGSHARE_VERSION) except PathAccessError: pass @@ -247,7 +247,7 @@ def verify(a, b): b_doi = glom(b, "ext_ids.doi") versioned_doi_pattern = '10[.].*/v[0-9]{1,}$' if re.match(versioned_doi_pattern, a_doi) and re.match(versioned_doi_pattern, b_doi): - return (Status.STRONG, OK.VERSIONED_DOI) + return (Status.STRONG, Reason.VERSIONED_DOI) except PathAccessError: pass @@ -258,7 +258,7 @@ def verify(a, b): a_doi = glom(a, "ext_ids.doi") b_doi = glom(b, "ext_ids.doi") if a_doi.split(".")[:-1] == b_doi.split(".") or a_doi.split(".") == b_doi.split(".")[:-1]: - return (Status.STRONG, OK.VERSIONED_DOI) + return (Status.STRONG, Reason.VERSIONED_DOI) except PathAccessError: pass @@ -291,7 +291,7 @@ def verify(a, b): b_doi_rel = get_datacite_related_doi(b) try: if glom(b, "ext_ids.doi") in a_doi_rel or glom(a, "ext_ids.doi") in b_doi_rel: - return (Status.STRONG, OK.DATACITE_RELATED_ID) + return (Status.STRONG, Reason.DATACITE_RELATED_ID) except PathAccessError: pass @@ -299,7 +299,7 @@ def verify(a, b): id_a = re.match(r"(.*)v[0-9]{1,}$", glom(a, "ext_ids.arxiv")).group(1) id_b = re.match(r"(.*)v[0-9]{1,}$", glom(b, "ext_ids.arxiv")).group(1) if id_a == id_b: - return (Status.STRONG, OK.ARXIV_VERSION) + return (Status.STRONG, Reason.ARXIV_VERSION) except (AttributeError, ValueError, PathAccessError) as exc: pass @@ -320,31 +320,31 @@ def verify(a, b): "paper-conference", ]) if len(types & ignore_release_types) == 0: - return (Status.DIFFERENT, Miss.RELEASE_TYPE) + return (Status.DIFFERENT, Reason.RELEASE_TYPE) if "dataset" in types and ("article" in types or "article-journal" in types): - return (Status.DIFFERENT, Miss.RELEASE_TYPE) + return (Status.DIFFERENT, Reason.RELEASE_TYPE) if "book" in types and ("article" in types or "article-journal" in types): - return (Status.DIFFERENT, Miss.RELEASE_TYPE) + return (Status.DIFFERENT, Reason.RELEASE_TYPE) except PathAccessError: pass try: if (glom(a, "release_type") == "dataset" and glom(b, "release_type") == "dataset" and glom(a, "ext_ids.doi") != glom(b, "ext_ids.doi")): - return (Status.DIFFERENT, Miss.DATASET_DOI) + return (Status.DIFFERENT, Reason.DATASET_DOI) except PathAccessError: pass try: if (glom(a, "release_type") == "chapter" and glom(b, "release_type") == "chapter" and glom(a, "extra.container_name") != glom(b, "extra.container_name")): - return (Status.DIFFERENT, Miss.BOOK_CHAPTER) + return (Status.DIFFERENT, Reason.BOOK_CHAPTER) except PathAccessError: pass try: if glom(a, "extra.crossref.type") == "component" and glom(a, "title") != glom(b, "title"): - return (Status.DIFFERENT, Miss.COMPONENT) + return (Status.DIFFERENT, Reason.COMPONENT) except PathAccessError: pass @@ -353,7 +353,7 @@ def verify(a, b): a_doi = glom(a, "ext_ids.doi") b_doi = glom(b, "ext_ids.doi") if a_doi != b_doi: - return (Status.DIFFERENT, Miss.COMPONENT) + return (Status.DIFFERENT, Reason.COMPONENT) except PathAccessError: pass @@ -367,7 +367,7 @@ def verify(a, b): a_year = a.get("release_year") b_year = b.get("release_year") if a_year and b_year and abs(a_year - b_year) > 40: - return (Status.DIFFERENT, Miss.YEAR) + return (Status.DIFFERENT, Reason.YEAR) if a_slug_title == b_slug_title: # via: https://fatcat.wiki/release/ij3yuoh6lrh3tkrv5o7gfk6yyi @@ -376,7 +376,7 @@ def verify(a, b): try: if (glom(a, "ext_ids.doi").split("/")[0] == "10.1109" and glom(b, "ext_ids.arxiv") != ""): - return (Status.STRONG, OK.CUSTOM_IEEE_ARXIV) + return (Status.STRONG, Reason.CUSTOM_IEEE_ARXIV) except PathAccessError: pass @@ -396,7 +396,7 @@ def verify(a, b): a_doi = glom(a, "ext_ids.doi") b_doi = glom(b, "ext_ids.doi") if has_doi_prefix(a_doi, "10.7916") and has_doi_prefix(b_doi, "10.7916"): - return (Status.AMBIGUOUS, Miss.CUSTOM_PREFIX_10_7916) + return (Status.AMBIGUOUS, Reason.CUSTOM_PREFIX_10_7916) except PathAccessError: pass @@ -407,7 +407,7 @@ def verify(a, b): for a_sub in a_subtitles: for b_sub in b_subtitles: if slugify_string(a_sub) != slugify_string(b_sub): - return (Status.DIFFERENT, Miss.SUBTITLE) + return (Status.DIFFERENT, Reason.SUBTITLE) except PathAccessError: pass @@ -429,54 +429,54 @@ def verify(a, b): # year; compromise allow a small gap if a_release_year and b_release_year and abs(int(a_release_year) - int(b_release_year)) > 1: - return (Status.DIFFERENT, Miss.YEAR) - return (Status.EXACT, OK.TITLE_AUTHOR_MATCH) + return (Status.DIFFERENT, Reason.YEAR) + return (Status.EXACT, Reason.TITLE_AUTHOR_MATCH) if (len(a.get("title", "").split()) == 1 and re.match(r".*[.][a-z]{2,3}", a.get("title", "")) or len(b.get("title", "").split()) == 1 and re.match(r".*[.][a-z]{2,3}$", b.get("title", ""))): if a.get("title") != b.get("title"): - return (Status.DIFFERENT, Miss.TITLE_FILENAME) + return (Status.DIFFERENT, Reason.TITLE_FILENAME) if a.get("title") and a.get("title") == b.get("title"): if a_release_year and b_release_year: if abs(int(a_release_year) - int(b_release_year)) > 2: - return (Status.DIFFERENT, Miss.YEAR) + return (Status.DIFFERENT, Reason.YEAR) if contains_chemical_formula(a_slug_title) or contains_chemical_formula(b_slug_title) and ( a_slug_title != b_slug_title): - return (Status.DIFFERENT, Miss.CHEM_FORMULA) + return (Status.DIFFERENT, Reason.CHEM_FORMULA) if len(a_slug_title) < 10 and a_slug_title != b_slug_title: - return (Status.AMBIGUOUS, Miss.SHORT_TITLE) + return (Status.AMBIGUOUS, Reason.SHORT_TITLE) if re.search(r'\d+', a_slug_title) and a_slug_title != b_slug_title and num_project( a_slug_title) == num_project(b_slug_title): - return (Status.DIFFERENT, Miss.NUM_DIFF) + return (Status.DIFFERENT, Reason.NUM_DIFF) if a_slug_title and b_slug_title and a_slug_title == b_slug_title: if a_authors and len(a_authors & b_authors) > 0: if arxiv_id_a is not None and arxiv_id_b is None or arxiv_id_a is None and arxiv_id_b is not None: - return (Status.STRONG, OK.PREPRINT_PUBLISHED) + return (Status.STRONG, Reason.PREPRINT_PUBLISHED) if a_slug_title and b_slug_title and a_slug_title.strip().replace( " ", "") == b_slug_title.strip().replace(" ", ""): if len(a_slug_authors & b_slug_authors) > 0: - return (Status.STRONG, OK.SLUG_TITLE_AUTHOR_MATCH) + return (Status.STRONG, Reason.SLUG_TITLE_AUTHOR_MATCH) # if any([a_authors, b_authors]) and not (a_authors and b_authors): # Does not cover case, where both authors are empty. if a_release_year == b_release_year and a_title_lower == b_title_lower: if ((dict_key_exists(a, "ext_ids.pmid") and dict_key_exists(b, "ext_ids.doi")) or (dict_key_exists(b, "ext_ids.pmid") and dict_key_exists(a, "ext_ids.doi"))): - return (Status.STRONG, OK.PMID_DOI_PAIR) + return (Status.STRONG, Reason.PMID_DOI_PAIR) # Two JSTOR items will probably be different. try: a_jstor_id = glom(a, "ext_ids.jstor") b_jstor_id = glom(b, "ext_ids.jstor") if a_jstor_id != b_jstor_id: - return (Status.DIFFERENT, Miss.JSTOR_ID) + return (Status.DIFFERENT, Reason.JSTOR_ID) except PathAccessError: pass @@ -490,7 +490,7 @@ def verify(a, b): if a_container_id == b_container_id and a_doi != b_doi and not has_doi_prefix( a_doi, "10.1126"): - return (Status.DIFFERENT, Miss.SHARED_DOI_PREFIX) + return (Status.DIFFERENT, Reason.SHARED_DOI_PREFIX) except PathAccessError: pass @@ -515,7 +515,7 @@ def verify(a, b): if len(top_scores) > 0: avg_score = sum(top_scores) / len(top_scores) if avg_score > 0.5: - return (Status.STRONG, OK.TOKENIZED_AUTHORS) + return (Status.STRONG, Reason.TOKENIZED_AUTHORS) else: pass # Kuidong Xu, Joong Ki Choi, Eun Jin Yang, Kyu Chul Lee, Yanli Lei @@ -530,19 +530,19 @@ def verify(a, b): a_tok = [tok for tok in re.findall(r"[\w]{3,}", " ".join(a_slug_authors)) if tok] b_tok = [tok for tok in re.findall(r"[\w]{3,}", " ".join(b_slug_authors)) if tok] if jaccard(set(a_tok), set(b_tok)) > 0.35: - return (Status.STRONG, OK.JACCARD_AUTHORS) + return (Status.STRONG, Reason.JACCARD_AUTHORS) # TODO: This misses spelling differences, e.g. # https://fatcat.wiki/release/7nbcgsohrrak5cuyk6dnit6ega and # https://fatcat.wiki/release/q66xv7drk5fnph7enwwlkyuwqm - return (Status.DIFFERENT, Miss.CONTRIB_INTERSECTION_EMPTY) + return (Status.DIFFERENT, Reason.CONTRIB_INTERSECTION_EMPTY) # mark choicereview articles as ambiguous, as they seem to be behind a paywall try: a_doi = glom(a, "ext_ids.doi") b_doi = glom(b, "ext_ids.doi") if has_doi_prefix(a_doi, "10.5860") or has_doi_prefix(b_doi, "10.5860"): - return (Status.AMBIGUOUS, Miss.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW) + return (Status.AMBIGUOUS, Reason.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW) except PathAccessError: pass @@ -562,8 +562,8 @@ def verify(a, b): b_num_pages = int(b_end) - int(b_start) if a_num_pages >= 0 and b_num_pages >= 0: if abs(a_num_pages - b_num_pages) > 5: - return (Status.DIFFERENT, Miss.PAGE_COUNT) + return (Status.DIFFERENT, Reason.PAGE_COUNT) except PathAccessError: pass - return (Status.AMBIGUOUS, OK.DUMMY) + return (Status.AMBIGUOUS, Reason.DUMMY) diff --git a/tests/data/verify.csv b/tests/data/verify.csv index 5a4f06d..8394744 100644 --- a/tests/data/verify.csv +++ b/tests/data/verify.csv @@ -1,165 +1,165 @@ -7kzrmoajzzedxgdvbltgqihszu,bd4crw4p7ber7pzhpoyw2c77bi,Status.STRONG,OK.DATACITE_RELATED_ID -foddwpevbjao3b3uwccvtuxfi4,versjalccvgdtp3q25elgy2z7a,Status.DIFFERENT,Miss.DATASET_DOI -v2ypxs2yrbh57cdo6lfuiik64e,6zzx36tlefdtbftzpg4wtump3e,Status.EXACT,OK.WORK_ID -hdvg6m467bhyng4l7xauk4ymoa,f5fugxp3qze2fht2uxt3xivi4i,Status.EXACT,OK.WORK_ID -cubz67ifbvacppya3i27yiwr2q,4ojllezvyfehnpnj2pil2h2pdu,Status.EXACT,OK.TITLE_AUTHOR_MATCH -s46mfwvb4rdyhlforb6yxg3abi,5hvdhbszafhw5fbu4jnrmesdmu,Status.DIFFERENT,Miss.BOOK_CHAPTER -mn26hwbmqvh23jhsecoder3ixq,544v67u75fazfp5qssqzmh6fta,Status.DIFFERENT,Miss.YEAR -4srjsirjhvhvtenz23lg6bqnqu,3czbwace7bh4hkfehzntnddt2i,Status.EXACT,OK.WORK_ID -vokr6qxyqrc55kyn45dyavr2lq,b5helm53ljdxjpxdnn5zjqpjve,Status.EXACT,OK.WORK_ID -kgeynply6vcxdeiluu6es6w72m,cm536ige6bfdfhhesp26ibfdva,Status.EXACT,OK.DATACITE_VERSION -knwc764q25f33ib6qnwo7pyaui,n74tqiqi5jcx5d6vl5f7lpokaa,Status.DIFFERENT,Miss.YEAR -eo4qptzoqrholjslj7nemlne2y,zisq3tsezjcejinlpf7qgk6z2i,Status.DIFFERENT,Miss.YEAR -crsd5c2fhvd7hodbd4trne3lgi,4547ybo5hvf4xhlh5triaccxai,Status.DIFFERENT,Miss.YEAR -egxon2iqljf47c4stvacnccvwy,swuxb5owx5g4hff3c7ur5x3awy,Status.DIFFERENT,Miss.YEAR -kob434ccgbhu3ecnwnqzsb6e3a,wbw3dpl44zew3bjcwfvqtk2b2q,Status.AMBIGUOUS,OK.DUMMY -c2pranaprjhrxk7x5euws32cg4,liarb7xuizewdafcubg2z3dwou,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -tyokc7ccfjaw5nimkkl32dl6ta,gyyxomlfkzfannusvzoypbnel4,Status.AMBIGUOUS,Miss.BLACKLISTED -2wakwcyb2zhbla2aao3g6ajfli,dryvgf7v3jeergr3gendplglqq,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -zvwqju7e3zhf7jpbtoejfe3i4y,fpj5eqgiunfpjn7qkffwvpre5e,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -cwfhdsdr6nbtngqwsqpafqj72u,icrvubkwprh6fl2irtrxziqqai,Status.EXACT,OK.WORK_ID -qlkjwemcrzcpjeeecduiunghui,chejpgnhebcx7of4d4dkuqhkne,Status.DIFFERENT,Miss.YEAR -no7a4vrfwnfp7jqrliq6n2hpxi,rscsor4cl5fydedr2jb6o7k4zi,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -mxfrtcc3njeh5dscwgzhrugzsq,x7lbkuc5afb75nz5l5kyrzy2ia,Status.DIFFERENT,Miss.YEAR -cqkm3hyn3rgcng3d3alwtciwpq,unwrwze6znf5xouud35i3jlneq,Status.EXACT,OK.WORK_ID -fzs6y277zbgxnbcsmmfnftyqgy,b2ggrb2mpvh4namvf6mht5nnaq,Status.DIFFERENT,Miss.YEAR -qgvu7i5eqrakpcnantqikaxpbu,kafrljfrv5favpvbgxavobh46y,Status.AMBIGUOUS,Miss.SHORT_TITLE -qbfao6tzh5gkxaqaqwmidpme3q,whyzodcvtzehjdvj5ezvbkda34,Status.DIFFERENT,Miss.SUBTITLE -ml7eci5bmnc4zl6fc6vzscciwu,rsjv7rxzuzdptmfn7orwxr7n6q,Status.EXACT,OK.WORK_ID -3mup7xynsfdpne3rtp274lmwdy,pbhkek57zrddnllui7pl4vjhai,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -lr5emu7qpfdmve6jcfjlrgoi64,revp263aa5dnjft72qynhzjcvi,Status.DIFFERENT,Miss.YEAR -bvu4qrzfvfdhxpvl4k2ertxkbe,qnteujy54vflrnjtq2k4wtrabq,Status.DIFFERENT,Miss.YEAR -gzmkqlwx4vd7vdtnlhkd2md2wy,7uu7g6k7grbrzlhhibf4q55odm,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -apbr2crzrfamhdqt35c3sgkld4,fwhmikkv7rcjdp6j6vmroggncy,Status.STRONG,OK.SLUG_TITLE_AUTHOR_MATCH -3x5gxfal75geppn22rck3bdanm,fpjygddf7bgahaaabjl2d67m4i,Status.EXACT,OK.TITLE_AUTHOR_MATCH -mkqmxbrhozhxphemdgshl57m3u,ahlp3vywzzb5fh5tbjskaym3ri,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -2hquztvjlrai3frazkmb6icgzy,ygkmoig5fjhtbg3rcobuy67pnu,Status.AMBIGUOUS,Miss.SHORT_TITLE -uzrpjthgpbb2hhacohndcgj3qm,gxbp2vmubnhgrhfobb7wceujvm,Status.EXACT,OK.WORK_ID -fmeud4dykjfudb5kjr2fgmaneq,iid2bnrjjbegtpgmpuppjou4k4,Status.DIFFERENT,Miss.SUBTITLE -zmivcpjvhba25ldkx27d24oefa,mjapiqe2nzcy3fs3hriw253dye,Status.STRONG,OK.FIGSHARE_VERSION -lynlkp7wh5hn3mlpzcfz4faoqi,yrbvjd4xrjaq3jxt7pkheysclm,Status.DIFFERENT,Miss.YEAR -t3vpox5wrvbgtcigp6a6o64oey,q5yaj5zbzjctzapb5bztzctsoe,Status.DIFFERENT,Miss.YEAR -65qtai5dmjb2hmkwa73nwafyhu,p4lk4tbohjat3g5nn5pb3kjdyu,Status.DIFFERENT,Miss.RELEASE_TYPE -fqtc2tonfbh7hlcwoxgxzqi4lu,ng7utp7murge3ksuzbtljf5bsq,Status.DIFFERENT,Miss.YEAR -mbnr3nrdijerto6wfjnlsmfhga,ddikrsxnajblvchthiwcbsmiue,Status.STRONG,OK.DATACITE_RELATED_ID -nqfv37as6bcohketfrhiuac2mq,ty6megtz35c3hep57bbx2cetja,Status.DIFFERENT,Miss.YEAR -cedhaxcvkrddpeedqtaxln4zsq,5hzpesjrjrdrzaoahvihorp7eq,Status.EXACT,OK.WORK_ID -wwiarqhsgbevdc74f6i4qmvyhy,d35gplnuibe6djfhnh42o66zbm,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -arzle77ezbbz5e33ghpqlwjw5e,e6ism7bt2vf5jl4v2ffwy3gqvu,Status.DIFFERENT,Miss.SUBTITLE -yv3ihfy6pfe4xblrj7dcf3674u,tmewuet24jg5dflspneju2cot4,Status.EXACT,OK.WORK_ID -rh3r3fncmzaulfdfrjzv25tpli,7zp3azvi4vbxxob2cdyzm6pepa,Status.EXACT,OK.TITLE_AUTHOR_MATCH -lf7w27ma2ncjjpwoy2kl22t77e,mgxkqlohmbhfpedxwg3s5jhrrq,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -libbt4mcwng3tiwcutfaxewmjy,6csob32ld5dx7h63cssqly6rfm,Status.DIFFERENT,Miss.YEAR -2r6dem2qanfttn73lezeislize,4iksfoith5b6zjarfihdtosr3e,Status.EXACT,OK.WORK_ID -wif435fwunfpfd46vvxo3at5ya,fy3j2l4s55b7ffltpiaic2jj7i,Status.DIFFERENT,Miss.YEAR -huophilkpbh2ddemt7okzzkuyq,crle5axqrfhfdob464wlwhfrf4,Status.AMBIGUOUS,Miss.SHORT_TITLE -dcq2jgd5abbjflzun4n3v6gjh4,ptovjgczrvft5fq2plyldafniq,Status.DIFFERENT,Miss.YEAR -7ah6efvk2ncjzgywch2cmtfumq,nj7v4e3cxbfybozjmdiuwqo4sm,Status.DIFFERENT,Miss.RELEASE_TYPE -eu4xst6zx5atfj37mvwdm54opq,7b7vnb7bc5g5va4yk72ruajok4,Status.STRONG,OK.FIGSHARE_VERSION -6ovhnujfsff2nhnoeimjcckgta,qeujgsfrmvft7k7r474maekvua,Status.DIFFERENT,Miss.DATASET_DOI -muk4xhjhubc3xn6qqddllgfsly,2gywie7yqfflnl6tljfo36keqi,Status.EXACT,OK.WORK_ID -iywyis7npngxxbco6fgjrclrzy,anhsfjxg3few5nkfsvheehiebq,Status.DIFFERENT,Miss.BOOK_CHAPTER -rk7mn5uaqjaslgcxc2nl6ijpaq,td3rnxzbxzeslj6ijoce3mtxcq,Status.EXACT,OK.WORK_ID -ohkfrjjcxfcavoqoqt52wi6eke,egufgu3yubgthex3y7fdt7uupa,Status.DIFFERENT,Miss.DATASET_DOI -dklwsz4w3rdlfddif4pcxb6ngm,wsbinmv7lragjnaedbgws6bztm,Status.DIFFERENT,Miss.RELEASE_TYPE -jizydliu2vclvpdtcrajlvuq2m,3g6mdd3tvjabdaez6mwcycso3q,Status.EXACT,OK.WORK_ID -fvrscdvsznb4zlhuadd6ar7ot4,57la45yryjd73gav22bnl4lyni,Status.STRONG,OK.FIGSHARE_VERSION -6fedywjyynbxhdqv3etxjuqhba,gls2x7ca4nhzrkf437gdnj6ekq,Status.DIFFERENT,Miss.YEAR -7lepq6lyyfepdjat6ohpeqycdu,cfm6qhhxovferl2fahf6jmcsiu,Status.DIFFERENT,Miss.YEAR -ijbm7t2mpjcrrjazrmeli6b42a,7ijg4ar62rgo3olfbxltltrzc4,Status.EXACT,OK.WORK_ID -hyt2ebpmhjg53f5eu4v5zortfm,ceu2t7fapvg43bvyyqck344pei,Status.DIFFERENT,Miss.SUBTITLE -uhih3c4gbzdtnciiqlfjx3w6le,lgga6cjz6bgo7cszpjfhpuoaqi,Status.DIFFERENT,Miss.YEAR -53w5pycrmvgglludwsv44m3czu,mvdjwqdvxfh3vd3zotf3gljm4a,Status.DIFFERENT,Miss.SUBTITLE -6vejogvunnbb7etjzu4yfs32mm,g53ggmce2rek5lw2l52oaimgiq,Status.DIFFERENT,Miss.SUBTITLE -325je3kjkjeerkchimvz6qxyji,ir7i7ldr7ffuvigvv6cvyyc7ju,Status.DIFFERENT,Miss.BOOK_CHAPTER -hqwrsqnzdjbqhbrqnsbooohqse,ydx2wolhvffxnb6as6gekmocx4,Status.EXACT,OK.WORK_ID -vz7q453kr5ds3ptsldwxedbiii,2wzybzqlmjhjfh75cxjohbvzi4,Status.DIFFERENT,Miss.RELEASE_TYPE -efumvvpw6jbb7ehp2qfdatgxzy,funn7cwjbrgefji27tzpl4avuu,Status.EXACT,OK.WORK_ID -pjvosq3ulzeb5d6w7zijrbz75y,pxkm2asxjnflzkdi5qnfd5fpt4,Status.DIFFERENT,Miss.BOOK_CHAPTER -ji3qg5sajndt7p54u7wumqsjye,hxau2e34bnhhbeucfdrncgmcby,Status.DIFFERENT,Miss.YEAR +7kzrmoajzzedxgdvbltgqihszu,bd4crw4p7ber7pzhpoyw2c77bi,Status.STRONG,DATACITE_RELATED_ID +foddwpevbjao3b3uwccvtuxfi4,versjalccvgdtp3q25elgy2z7a,Status.DIFFERENT,DATASET_DOI +v2ypxs2yrbh57cdo6lfuiik64e,6zzx36tlefdtbftzpg4wtump3e,Status.EXACT,WORK_ID +hdvg6m467bhyng4l7xauk4ymoa,f5fugxp3qze2fht2uxt3xivi4i,Status.EXACT,WORK_ID +cubz67ifbvacppya3i27yiwr2q,4ojllezvyfehnpnj2pil2h2pdu,Status.EXACT,TITLE_AUTHOR_MATCH +s46mfwvb4rdyhlforb6yxg3abi,5hvdhbszafhw5fbu4jnrmesdmu,Status.DIFFERENT,BOOK_CHAPTER +mn26hwbmqvh23jhsecoder3ixq,544v67u75fazfp5qssqzmh6fta,Status.DIFFERENT,YEAR +4srjsirjhvhvtenz23lg6bqnqu,3czbwace7bh4hkfehzntnddt2i,Status.EXACT,WORK_ID +vokr6qxyqrc55kyn45dyavr2lq,b5helm53ljdxjpxdnn5zjqpjve,Status.EXACT,WORK_ID +kgeynply6vcxdeiluu6es6w72m,cm536ige6bfdfhhesp26ibfdva,Status.EXACT,DATACITE_VERSION +knwc764q25f33ib6qnwo7pyaui,n74tqiqi5jcx5d6vl5f7lpokaa,Status.DIFFERENT,YEAR +eo4qptzoqrholjslj7nemlne2y,zisq3tsezjcejinlpf7qgk6z2i,Status.DIFFERENT,YEAR +crsd5c2fhvd7hodbd4trne3lgi,4547ybo5hvf4xhlh5triaccxai,Status.DIFFERENT,YEAR +egxon2iqljf47c4stvacnccvwy,swuxb5owx5g4hff3c7ur5x3awy,Status.DIFFERENT,YEAR +kob434ccgbhu3ecnwnqzsb6e3a,wbw3dpl44zew3bjcwfvqtk2b2q,Status.AMBIGUOUS,DUMMY +c2pranaprjhrxk7x5euws32cg4,liarb7xuizewdafcubg2z3dwou,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +tyokc7ccfjaw5nimkkl32dl6ta,gyyxomlfkzfannusvzoypbnel4,Status.AMBIGUOUS,BLACKLISTED +2wakwcyb2zhbla2aao3g6ajfli,dryvgf7v3jeergr3gendplglqq,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +zvwqju7e3zhf7jpbtoejfe3i4y,fpj5eqgiunfpjn7qkffwvpre5e,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +cwfhdsdr6nbtngqwsqpafqj72u,icrvubkwprh6fl2irtrxziqqai,Status.EXACT,WORK_ID +qlkjwemcrzcpjeeecduiunghui,chejpgnhebcx7of4d4dkuqhkne,Status.DIFFERENT,YEAR +no7a4vrfwnfp7jqrliq6n2hpxi,rscsor4cl5fydedr2jb6o7k4zi,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +mxfrtcc3njeh5dscwgzhrugzsq,x7lbkuc5afb75nz5l5kyrzy2ia,Status.DIFFERENT,YEAR +cqkm3hyn3rgcng3d3alwtciwpq,unwrwze6znf5xouud35i3jlneq,Status.EXACT,WORK_ID +fzs6y277zbgxnbcsmmfnftyqgy,b2ggrb2mpvh4namvf6mht5nnaq,Status.DIFFERENT,YEAR +qgvu7i5eqrakpcnantqikaxpbu,kafrljfrv5favpvbgxavobh46y,Status.AMBIGUOUS,SHORT_TITLE +qbfao6tzh5gkxaqaqwmidpme3q,whyzodcvtzehjdvj5ezvbkda34,Status.DIFFERENT,SUBTITLE +ml7eci5bmnc4zl6fc6vzscciwu,rsjv7rxzuzdptmfn7orwxr7n6q,Status.EXACT,WORK_ID +3mup7xynsfdpne3rtp274lmwdy,pbhkek57zrddnllui7pl4vjhai,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +lr5emu7qpfdmve6jcfjlrgoi64,revp263aa5dnjft72qynhzjcvi,Status.DIFFERENT,YEAR +bvu4qrzfvfdhxpvl4k2ertxkbe,qnteujy54vflrnjtq2k4wtrabq,Status.DIFFERENT,YEAR +gzmkqlwx4vd7vdtnlhkd2md2wy,7uu7g6k7grbrzlhhibf4q55odm,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +apbr2crzrfamhdqt35c3sgkld4,fwhmikkv7rcjdp6j6vmroggncy,Status.STRONG,SLUG_TITLE_AUTHOR_MATCH +3x5gxfal75geppn22rck3bdanm,fpjygddf7bgahaaabjl2d67m4i,Status.EXACT,TITLE_AUTHOR_MATCH +mkqmxbrhozhxphemdgshl57m3u,ahlp3vywzzb5fh5tbjskaym3ri,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +2hquztvjlrai3frazkmb6icgzy,ygkmoig5fjhtbg3rcobuy67pnu,Status.AMBIGUOUS,SHORT_TITLE +uzrpjthgpbb2hhacohndcgj3qm,gxbp2vmubnhgrhfobb7wceujvm,Status.EXACT,WORK_ID +fmeud4dykjfudb5kjr2fgmaneq,iid2bnrjjbegtpgmpuppjou4k4,Status.DIFFERENT,SUBTITLE +zmivcpjvhba25ldkx27d24oefa,mjapiqe2nzcy3fs3hriw253dye,Status.STRONG,FIGSHARE_VERSION +lynlkp7wh5hn3mlpzcfz4faoqi,yrbvjd4xrjaq3jxt7pkheysclm,Status.DIFFERENT,YEAR +t3vpox5wrvbgtcigp6a6o64oey,q5yaj5zbzjctzapb5bztzctsoe,Status.DIFFERENT,YEAR +65qtai5dmjb2hmkwa73nwafyhu,p4lk4tbohjat3g5nn5pb3kjdyu,Status.DIFFERENT,RELEASE_TYPE +fqtc2tonfbh7hlcwoxgxzqi4lu,ng7utp7murge3ksuzbtljf5bsq,Status.DIFFERENT,YEAR +mbnr3nrdijerto6wfjnlsmfhga,ddikrsxnajblvchthiwcbsmiue,Status.STRONG,DATACITE_RELATED_ID +nqfv37as6bcohketfrhiuac2mq,ty6megtz35c3hep57bbx2cetja,Status.DIFFERENT,YEAR +cedhaxcvkrddpeedqtaxln4zsq,5hzpesjrjrdrzaoahvihorp7eq,Status.EXACT,WORK_ID +wwiarqhsgbevdc74f6i4qmvyhy,d35gplnuibe6djfhnh42o66zbm,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +arzle77ezbbz5e33ghpqlwjw5e,e6ism7bt2vf5jl4v2ffwy3gqvu,Status.DIFFERENT,SUBTITLE +yv3ihfy6pfe4xblrj7dcf3674u,tmewuet24jg5dflspneju2cot4,Status.EXACT,WORK_ID +rh3r3fncmzaulfdfrjzv25tpli,7zp3azvi4vbxxob2cdyzm6pepa,Status.EXACT,TITLE_AUTHOR_MATCH +lf7w27ma2ncjjpwoy2kl22t77e,mgxkqlohmbhfpedxwg3s5jhrrq,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +libbt4mcwng3tiwcutfaxewmjy,6csob32ld5dx7h63cssqly6rfm,Status.DIFFERENT,YEAR +2r6dem2qanfttn73lezeislize,4iksfoith5b6zjarfihdtosr3e,Status.EXACT,WORK_ID +wif435fwunfpfd46vvxo3at5ya,fy3j2l4s55b7ffltpiaic2jj7i,Status.DIFFERENT,YEAR +huophilkpbh2ddemt7okzzkuyq,crle5axqrfhfdob464wlwhfrf4,Status.AMBIGUOUS,SHORT_TITLE +dcq2jgd5abbjflzun4n3v6gjh4,ptovjgczrvft5fq2plyldafniq,Status.DIFFERENT,YEAR +7ah6efvk2ncjzgywch2cmtfumq,nj7v4e3cxbfybozjmdiuwqo4sm,Status.DIFFERENT,RELEASE_TYPE +eu4xst6zx5atfj37mvwdm54opq,7b7vnb7bc5g5va4yk72ruajok4,Status.STRONG,FIGSHARE_VERSION +6ovhnujfsff2nhnoeimjcckgta,qeujgsfrmvft7k7r474maekvua,Status.DIFFERENT,DATASET_DOI +muk4xhjhubc3xn6qqddllgfsly,2gywie7yqfflnl6tljfo36keqi,Status.EXACT,WORK_ID +iywyis7npngxxbco6fgjrclrzy,anhsfjxg3few5nkfsvheehiebq,Status.DIFFERENT,BOOK_CHAPTER +rk7mn5uaqjaslgcxc2nl6ijpaq,td3rnxzbxzeslj6ijoce3mtxcq,Status.EXACT,WORK_ID +ohkfrjjcxfcavoqoqt52wi6eke,egufgu3yubgthex3y7fdt7uupa,Status.DIFFERENT,DATASET_DOI +dklwsz4w3rdlfddif4pcxb6ngm,wsbinmv7lragjnaedbgws6bztm,Status.DIFFERENT,RELEASE_TYPE +jizydliu2vclvpdtcrajlvuq2m,3g6mdd3tvjabdaez6mwcycso3q,Status.EXACT,WORK_ID +fvrscdvsznb4zlhuadd6ar7ot4,57la45yryjd73gav22bnl4lyni,Status.STRONG,FIGSHARE_VERSION +6fedywjyynbxhdqv3etxjuqhba,gls2x7ca4nhzrkf437gdnj6ekq,Status.DIFFERENT,YEAR +7lepq6lyyfepdjat6ohpeqycdu,cfm6qhhxovferl2fahf6jmcsiu,Status.DIFFERENT,YEAR +ijbm7t2mpjcrrjazrmeli6b42a,7ijg4ar62rgo3olfbxltltrzc4,Status.EXACT,WORK_ID +hyt2ebpmhjg53f5eu4v5zortfm,ceu2t7fapvg43bvyyqck344pei,Status.DIFFERENT,SUBTITLE +uhih3c4gbzdtnciiqlfjx3w6le,lgga6cjz6bgo7cszpjfhpuoaqi,Status.DIFFERENT,YEAR +53w5pycrmvgglludwsv44m3czu,mvdjwqdvxfh3vd3zotf3gljm4a,Status.DIFFERENT,SUBTITLE +6vejogvunnbb7etjzu4yfs32mm,g53ggmce2rek5lw2l52oaimgiq,Status.DIFFERENT,SUBTITLE +325je3kjkjeerkchimvz6qxyji,ir7i7ldr7ffuvigvv6cvyyc7ju,Status.DIFFERENT,BOOK_CHAPTER +hqwrsqnzdjbqhbrqnsbooohqse,ydx2wolhvffxnb6as6gekmocx4,Status.EXACT,WORK_ID +vz7q453kr5ds3ptsldwxedbiii,2wzybzqlmjhjfh75cxjohbvzi4,Status.DIFFERENT,RELEASE_TYPE +efumvvpw6jbb7ehp2qfdatgxzy,funn7cwjbrgefji27tzpl4avuu,Status.EXACT,WORK_ID +pjvosq3ulzeb5d6w7zijrbz75y,pxkm2asxjnflzkdi5qnfd5fpt4,Status.DIFFERENT,BOOK_CHAPTER +ji3qg5sajndt7p54u7wumqsjye,hxau2e34bnhhbeucfdrncgmcby,Status.DIFFERENT,YEAR 2gpvznjjcfbmhats6ot2vsodju,qk6arua2snaobfvdvlfvjp3yeq,Status.AMBIGUOUS, 75ky5xniobchzbhzwhmwhu5uoa,uvgwfvwnnbg7xchy63bloyrwvi,Status.STRONG, jdtngtiz3bdqboypujoni2x3ry,byh7xr5qhjca3bw53ivdotck3e,Status.EXACT, 5lk635o65nc2tnkus3pkf2ggeq,hqrvhbvocvaabg6nr5p43tl3uq,Status.DIFFERENT, 5lk635o65nc2tnkus3pkf2ggeq,zfwf3tefajc6zdxa47vgilm7wm,Status.AMBIGUOUS, hqrvhbvocvaabg6nr5p43tl3uq,zfwf3tefajc6zdxa47vgilm7wm,Status.AMBIGUOUS, -ppnzru2opnhxlai7pcmo7phe4i,iitldffmnncijgnf6ujb6zmdfu,Status.DIFFERENT,Miss.NUM_DIFF -fv35r37pb5c5tioyqburswsute,poeywm5o4raljhatd6zvehcicy,Status.EXACT,OK.TITLE_AUTHOR_MATCH -s6znyezm4fdqfiihwcdtfapfqu,wz6kycfyqfdhhbcjteotw4jcbu,Status.STRONG,OK.PREPRINT_PUBLISHED -ocbjm53gxvavrhyupfqlynlq44,olhia3lm2jfsrg3jkisjjnowsu,Status.EXACT,OK.WORK_ID -ocbjm53gxvavrhyupfqlynlq44,twzjy7m5irdu5gjkvrsp65hefa,Status.EXACT,OK.WORK_ID -olhia3lm2jfsrg3jkisjjnowsu,twzjy7m5irdu5gjkvrsp65hefa,Status.EXACT,OK.WORK_ID -q5qkykfazfbahbson4uiopnq4q,s4rrmyvibvdatgj7hiduekcjhe,Status.EXACT,OK.TITLE_AUTHOR_MATCH -fuaz2iolhjegfpdmob3i3efvgm,uxzn4nznrfbttivwzdc7noptku,Status.EXACT,OK.TITLE_AUTHOR_MATCH -7j2dsplr45bhvdtrhqa7hykwka,pxzy4k45xjhgfgw6znf5xjayfa,Status.STRONG,OK.TOKENIZED_AUTHORS -7j2dsplr45bhvdtrhqa7hykwka,ud3tzdfacncvnkj232lkvvg34q,Status.EXACT,OK.DOI -pxzy4k45xjhgfgw6znf5xjayfa,ud3tzdfacncvnkj232lkvvg34q,Status.DIFFERENT,Miss.RELEASE_TYPE -b5p5i7phjfejhiecjaz4arkp3m,rzicki3gcjayxaic7ckyx6bcmq,Status.DIFFERENT,Miss.SHARED_DOI_PREFIX -bkonm3q2dbegde3i4sl6h6lkvq,hhyknlu55vdezg3xsqxa4as2eu,Status.EXACT,OK.TITLE_AUTHOR_MATCH -bkonm3q2dbegde3i4sl6h6lkvq,s7mpon5havhx3eil563hcz6anu,Status.EXACT,OK.DOI -hhyknlu55vdezg3xsqxa4as2eu,s7mpon5havhx3eil563hcz6anu,Status.EXACT,OK.TITLE_AUTHOR_MATCH -r63fa4mqkfb3leafypdwnnj7jq,usifdrmhdbfhlodgaqgzwzi4da,Status.DIFFERENT,Miss.SHARED_DOI_PREFIX +ppnzru2opnhxlai7pcmo7phe4i,iitldffmnncijgnf6ujb6zmdfu,Status.DIFFERENT,NUM_DIFF +fv35r37pb5c5tioyqburswsute,poeywm5o4raljhatd6zvehcicy,Status.EXACT,TITLE_AUTHOR_MATCH +s6znyezm4fdqfiihwcdtfapfqu,wz6kycfyqfdhhbcjteotw4jcbu,Status.STRONG,PREPRINT_PUBLISHED +ocbjm53gxvavrhyupfqlynlq44,olhia3lm2jfsrg3jkisjjnowsu,Status.EXACT,WORK_ID +ocbjm53gxvavrhyupfqlynlq44,twzjy7m5irdu5gjkvrsp65hefa,Status.EXACT,WORK_ID +olhia3lm2jfsrg3jkisjjnowsu,twzjy7m5irdu5gjkvrsp65hefa,Status.EXACT,WORK_ID +q5qkykfazfbahbson4uiopnq4q,s4rrmyvibvdatgj7hiduekcjhe,Status.EXACT,TITLE_AUTHOR_MATCH +fuaz2iolhjegfpdmob3i3efvgm,uxzn4nznrfbttivwzdc7noptku,Status.EXACT,TITLE_AUTHOR_MATCH +7j2dsplr45bhvdtrhqa7hykwka,pxzy4k45xjhgfgw6znf5xjayfa,Status.STRONG,TOKENIZED_AUTHORS +7j2dsplr45bhvdtrhqa7hykwka,ud3tzdfacncvnkj232lkvvg34q,Status.EXACT,DOI +pxzy4k45xjhgfgw6znf5xjayfa,ud3tzdfacncvnkj232lkvvg34q,Status.DIFFERENT,RELEASE_TYPE +b5p5i7phjfejhiecjaz4arkp3m,rzicki3gcjayxaic7ckyx6bcmq,Status.DIFFERENT,SHARED_DOI_PREFIX +bkonm3q2dbegde3i4sl6h6lkvq,hhyknlu55vdezg3xsqxa4as2eu,Status.EXACT,TITLE_AUTHOR_MATCH +bkonm3q2dbegde3i4sl6h6lkvq,s7mpon5havhx3eil563hcz6anu,Status.EXACT,DOI +hhyknlu55vdezg3xsqxa4as2eu,s7mpon5havhx3eil563hcz6anu,Status.EXACT,TITLE_AUTHOR_MATCH +r63fa4mqkfb3leafypdwnnj7jq,usifdrmhdbfhlodgaqgzwzi4da,Status.DIFFERENT,SHARED_DOI_PREFIX bg4gzikycnfvtkfwl5qnxeywwa,fbdg4rdgw5halgkhr4qcsex25y,Status.EXACT, omjj75lv4rayvcqmgmicnzf5ye,xxfujnvafrazbjw7kvh7bhmuvy,Status.DIFFERENT, -63g4ukdxajcqhdytqla6du3t3u,rz72bzfevzeofdeb342c6z45qu,Status.DIFFERENT,Miss.CUSTOM_PREFIX_10_14288 -ij3yuoh6lrh3tkrv5o7gfk6yyi,tur236mqljdfdnlzbbnks2sily,Status.STRONG,OK.CUSTOM_IEEE_ARXIV -neznj5fb4nf3tdqnotnbe34b6e,gcqdvvjiq5bphl7lpc4invi4vy,Status.STRONG,OK.CUSTOM_BSI_UNDATED -he334wpbobegxhptpkvvrufioq,td3ouhgtzbbe7ctevfnldqkoba,Status.EXACT,OK.DATACITE_VERSION -caxa7qbfqvg3bkgz4nwvapgnvi,rnso2swxzvfonemgzrth3arumi,Status.DIFFERENT,Miss.CONTAINER -ehu6pdvzvvcmdoyq4l2yf4vciu,2omou6ehgjccbe6yjvr4wgnsha,Status.AMBIGUOUS,Miss.BLACKLISTED_FRAGMENT -zkqujozrx5cnjitmglclt6heqq,urr2gs4dsbbwdl7asgyqnwwtxy,Status.AMBIGUOUS,Miss.BLACKLISTED_FRAGMENT -5b3lb2ebmrdp5nzxvohefmadre,yy2wzuaxhba7jht72mcjhxuaju,Status.DIFFERENT,Miss.CUSTOM_IOP_MA_PATTERN +63g4ukdxajcqhdytqla6du3t3u,rz72bzfevzeofdeb342c6z45qu,Status.DIFFERENT,CUSTOM_PREFIX_10_14288 +ij3yuoh6lrh3tkrv5o7gfk6yyi,tur236mqljdfdnlzbbnks2sily,Status.STRONG,CUSTOM_IEEE_ARXIV +neznj5fb4nf3tdqnotnbe34b6e,gcqdvvjiq5bphl7lpc4invi4vy,Status.STRONG,CUSTOM_BSI_UNDATED +he334wpbobegxhptpkvvrufioq,td3ouhgtzbbe7ctevfnldqkoba,Status.EXACT,DATACITE_VERSION +caxa7qbfqvg3bkgz4nwvapgnvi,rnso2swxzvfonemgzrth3arumi,Status.DIFFERENT,CONTAINER +ehu6pdvzvvcmdoyq4l2yf4vciu,2omou6ehgjccbe6yjvr4wgnsha,Status.AMBIGUOUS,BLACKLISTED_FRAGMENT +zkqujozrx5cnjitmglclt6heqq,urr2gs4dsbbwdl7asgyqnwwtxy,Status.AMBIGUOUS,BLACKLISTED_FRAGMENT +5b3lb2ebmrdp5nzxvohefmadre,yy2wzuaxhba7jht72mcjhxuaju,Status.DIFFERENT,CUSTOM_IOP_MA_PATTERN iwtrxnov2repzlgoi2at2md6tm,s5hm65waingwjmgf3plu76hzu4,Status.AMBIGUOUS, iwtrxnov2repzlgoi2at2md6tm,t6k5mec4xjdebcs3iv3uzs3yvu,Status.AMBIGUOUS, s5hm65waingwjmgf3plu76hzu4,t6k5mec4xjdebcs3iv3uzs3yvu,Status.AMBIGUOUS, -zlywxoy7cfexvaatziqp4ip5m4,phqelg6oc5hs5dehhgmodcnh5u,Status.EXACT,OK.DATACITE_VERSION -vqjpcuqxnbhdtelzspxjmklm7u,knuzh5bcqbg7ph7ffvqaiwevti,Status.AMBIGUOUS,Miss.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW -psykbwxylndtdaand2ymtkgzqu,xizkwvsodzajnn4u7lgeldqoum,Status.DIFFERENT,Miss.YEAR -nb4yakyqebalbatnnfijkfhmka,pr7e4l5eibaavm3zsk62nmphni,Status.STRONG,OK.SLUG_TITLE_AUTHOR_MATCH +zlywxoy7cfexvaatziqp4ip5m4,phqelg6oc5hs5dehhgmodcnh5u,Status.EXACT,DATACITE_VERSION +vqjpcuqxnbhdtelzspxjmklm7u,knuzh5bcqbg7ph7ffvqaiwevti,Status.AMBIGUOUS,CUSTOM_PREFIX_10_5860_CHOICE_REVIEW +psykbwxylndtdaand2ymtkgzqu,xizkwvsodzajnn4u7lgeldqoum,Status.DIFFERENT,YEAR +nb4yakyqebalbatnnfijkfhmka,pr7e4l5eibaavm3zsk62nmphni,Status.STRONG,SLUG_TITLE_AUTHOR_MATCH in2mm2wafbczjgzlapq55rrksq,oaezupjwnfckxaajjhjb3fl42e,Status.AMBIGUOUS, u4mjilmo75bcnjyms564l66jea,6ofr4mqnmrdy3nyyh5ufm5ats4,Status.AMBIGUOUS, -5a22nt42bvfj7m3dzfm7br73ni,63ht2plao5c4dasjeqj7vwglmq,Status.EXACT,OK.WORK_ID +5a22nt42bvfj7m3dzfm7br73ni,63ht2plao5c4dasjeqj7vwglmq,Status.EXACT,WORK_ID 5a22nt42bvfj7m3dzfm7br73ni,zchlsocreffbdm36qhzy3cs32e,Status.STRONG, 63ht2plao5c4dasjeqj7vwglmq,zchlsocreffbdm36qhzy3cs32e,Status.STRONG, -6ysfa7ncx5fldmvmwvjgpf2i6e,yp3rs3xb5ra2riyx5xayrlqfum,Status.EXACT,OK.WORK_ID -6ysfa7ncx5fldmvmwvjgpf2i6e,zphoquzqbfccjoqix3wkpyhrm4,Status.EXACT,OK.WORK_ID -yp3rs3xb5ra2riyx5xayrlqfum,zphoquzqbfccjoqix3wkpyhrm4,Status.EXACT,OK.WORK_ID -mz6a32xbp5f67i2cnbco2hmzj4,fo5dsqeocfekfhqdzgqyng3z6q,Status.AMBIGUOUS,Miss.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW -g2swo5fewnhv3ihmlpl32sojr4,ab2q56gokfdmzpccrmwfcdljgy,Status.AMBIGUOUS,Miss.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW -tmlg73royrdwdhl6nijf6m7vzy,3w4tibll4rdernjrn4hkkyqsem,Status.DIFFERENT,Miss.CONTRIB_INTERSECTION_EMPTY -eqcgtpav3na5jh56o5vjsvb4ei,7x7tszf54zggvp4xkrhakp667u,Status.STRONG,OK.PMID_DOI_PAIR -wm2p5fznwffknjx56lvmr7hn4q,idpgijvcsnbqrgs2dg36vzzdzm,Status.DIFFERENT,Miss.SHARED_DOI_PREFIX +6ysfa7ncx5fldmvmwvjgpf2i6e,yp3rs3xb5ra2riyx5xayrlqfum,Status.EXACT,WORK_ID +6ysfa7ncx5fldmvmwvjgpf2i6e,zphoquzqbfccjoqix3wkpyhrm4,Status.EXACT,WORK_ID +yp3rs3xb5ra2riyx5xayrlqfum,zphoquzqbfccjoqix3wkpyhrm4,Status.EXACT,WORK_ID +mz6a32xbp5f67i2cnbco2hmzj4,fo5dsqeocfekfhqdzgqyng3z6q,Status.AMBIGUOUS,CUSTOM_PREFIX_10_5860_CHOICE_REVIEW +g2swo5fewnhv3ihmlpl32sojr4,ab2q56gokfdmzpccrmwfcdljgy,Status.AMBIGUOUS,CUSTOM_PREFIX_10_5860_CHOICE_REVIEW +tmlg73royrdwdhl6nijf6m7vzy,3w4tibll4rdernjrn4hkkyqsem,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY +eqcgtpav3na5jh56o5vjsvb4ei,7x7tszf54zggvp4xkrhakp667u,Status.STRONG,PMID_DOI_PAIR +wm2p5fznwffknjx56lvmr7hn4q,idpgijvcsnbqrgs2dg36vzzdzm,Status.DIFFERENT,SHARED_DOI_PREFIX 72uzveph65ce7kfdct2wpgh5j4,nqcfu4il45aixekvk3rwflahdm,Status.DIFFERENT, mvvbim7kdffvtosuldtv5m3uy4,b7bbygyawzdsthai7j7rmztrxe,Status.DIFFERENT, -3f3yt32rrbdzdewtcyrcyihgju,hxmxijrd3fgodd3q3crgt7d3c4,Status.STRONG,OK.JACCARD_AUTHORS -dauh7n5w65enhk5zwdfwqxv344,jg72qhdvmncfdfxg5l47hw3uba,Status.DIFFERENT,Miss.COMPONENT -voruupqxhvggfex4zlczcmjxxu,jg72qhdvmncfdfxg5l47hw3uba,Status.AMBIGUOUS,OK.DUMMY -6ysfa7ncx5fldmvmwvjgpf2i6e,yp3rs3xb5ra2riyx5xayrlqfum,Status.EXACT,OK.WORK_ID +3f3yt32rrbdzdewtcyrcyihgju,hxmxijrd3fgodd3q3crgt7d3c4,Status.STRONG,JACCARD_AUTHORS +dauh7n5w65enhk5zwdfwqxv344,jg72qhdvmncfdfxg5l47hw3uba,Status.DIFFERENT,COMPONENT +voruupqxhvggfex4zlczcmjxxu,jg72qhdvmncfdfxg5l47hw3uba,Status.AMBIGUOUS,DUMMY +6ysfa7ncx5fldmvmwvjgpf2i6e,yp3rs3xb5ra2riyx5xayrlqfum,Status.EXACT,WORK_ID arqtphat7fashokettncepu7xe,v6p7xct6kfgwtdbh57zfjqmuua,Status.AMBIGUOUS, -zwru5ugcsfcyzeuqlygfw46vwq,b3uhit7b4vhvliocdzwxr7peyy,Status.AMBIGUOUS,Miss.CUSTOM_PREFIX_10_7916 -s7a4o5v5gfg4tbzna6poyg7nzy,tcro5wr6brhqnf5wettyiauw34,Status.STRONG,OK.CUSTOM_BSI_SUBDOC -eomug3y4afbynhcyzrtcvki55u,zcu2pugta5fttnqltgersan52q,Status.DIFFERENT,Miss.COMPONENT +zwru5ugcsfcyzeuqlygfw46vwq,b3uhit7b4vhvliocdzwxr7peyy,Status.AMBIGUOUS,CUSTOM_PREFIX_10_7916 +s7a4o5v5gfg4tbzna6poyg7nzy,tcro5wr6brhqnf5wettyiauw34,Status.STRONG,CUSTOM_BSI_SUBDOC +eomug3y4afbynhcyzrtcvki55u,zcu2pugta5fttnqltgersan52q,Status.DIFFERENT,COMPONENT f5ebjc63j5dzpct5hsme5j3ote,zeoquc2f4nbmdbmbcbkmkxmtzi,Status.AMBIGUOUS, -zvsffdeufjb5dbchww7ydqdq3a,5rcu6myqx5ezjjytzpvsauyut4,Status.STRONG,OK.PMID_DOI_PAIR -cd5aik2whrd5jlvleyvdq6iwja,kfttghqcsbddvofqd7l4bhtavy,Status.DIFFERENT,Miss.COMPONENT -hwnqyz7n65eabhlivvkipkytji,cwqujxztefdghhssb7ysxj7b5m,Status.STRONG,OK.VERSIONED_DOI +zvsffdeufjb5dbchww7ydqdq3a,5rcu6myqx5ezjjytzpvsauyut4,Status.STRONG,PMID_DOI_PAIR +cd5aik2whrd5jlvleyvdq6iwja,kfttghqcsbddvofqd7l4bhtavy,Status.DIFFERENT,COMPONENT +hwnqyz7n65eabhlivvkipkytji,cwqujxztefdghhssb7ysxj7b5m,Status.STRONG,VERSIONED_DOI yespzqkm2zed7n4vhjpkddap5e,5yixxzyl3vh4xd56lwcraowgty,Status.AMBIGUOUS, -pobnow7sxfhnxhltgwpru5k7oi,uplqxenmk5axjes6zokml6q73y,Status.DIFFERENT,Miss.RELEASE_TYPE -tm3gaiumkvb3xc7t3i6suna6u4,pobnow7sxfhnxhltgwpru5k7oi,Status.DIFFERENT,Miss.RELEASE_TYPE -lqswbciv2vfkzit5zamjaqik6m,zularouecbg5fg4nd6yswxf3s4,Status.DIFFERENT,Miss.JSTOR_ID +pobnow7sxfhnxhltgwpru5k7oi,uplqxenmk5axjes6zokml6q73y,Status.DIFFERENT,RELEASE_TYPE +tm3gaiumkvb3xc7t3i6suna6u4,pobnow7sxfhnxhltgwpru5k7oi,Status.DIFFERENT,RELEASE_TYPE +lqswbciv2vfkzit5zamjaqik6m,zularouecbg5fg4nd6yswxf3s4,Status.DIFFERENT,JSTOR_ID j6ipokw3lfflhl2de7afxhac2a,rbgpleyhanakxing2f3234d7xq,Status.AMBIGUOUS, -bruczmzvnzhtdkd2tf3meg3oou,a7wuehxrv5edpb5265qx27yvmy,Status.STRONG,OK.VERSIONED_DOI +bruczmzvnzhtdkd2tf3meg3oou,a7wuehxrv5edpb5265qx27yvmy,Status.STRONG,VERSIONED_DOI tebqkxnjpzfxnpsqmt5klv2ppm,uqyjav3arngq7bqmzsllxrkpmu,Status.DIFFERENT, e3fs7ttdbrds3bvsbm7lynzlpu,vpswmj3cgfhktggwvmz33fkwuq,Status.DIFFERENT, -gtsbvudmjzdeppqgzjpmfedycq,27lrseg7jfhxbdxohph7il7a7m,Status.DIFFERENT,Miss.JSTOR_ID -a3kmwzn4kjerbingv7oyfs5gwe,4m6ijk5gu5gxhcbvd2f4i2xk5u,Status.DIFFERENT,Miss.RELEASE_TYPE +gtsbvudmjzdeppqgzjpmfedycq,27lrseg7jfhxbdxohph7il7a7m,Status.DIFFERENT,JSTOR_ID +a3kmwzn4kjerbingv7oyfs5gwe,4m6ijk5gu5gxhcbvd2f4i2xk5u,Status.DIFFERENT,RELEASE_TYPE 254alcrrgfcz7l6j6kce7xqoli,kix6fwgliffudepddlnflom6pq,Status.AMBIGUOUS, s5gvgub2nvhazb5w7qae7w2dki,ac5cwyrtljgtji3jfgw3s2ckfe,Status.AMBIGUOUS, -qnblx3fetbegpe7ryt444dpkke,kokj44xkcfhxvorj7cs7rov2ku,Status.DIFFERENT,Miss.RELEASE_TYPE -vrwrf372jbd2vbwcb6fllsvhae,s43ecmng5bbqzcqhxmo7wbfsma,Status.DIFFERENT,Miss.RELEASE_TYPE -4z2amr4cizd2jexlr7uu4jxrsa,nvyd2rotrraelcuchnu6cjbxty,Status.STRONG,OK.PMID_DOI_PAIR +qnblx3fetbegpe7ryt444dpkke,kokj44xkcfhxvorj7cs7rov2ku,Status.DIFFERENT,RELEASE_TYPE +vrwrf372jbd2vbwcb6fllsvhae,s43ecmng5bbqzcqhxmo7wbfsma,Status.DIFFERENT,RELEASE_TYPE +4z2amr4cizd2jexlr7uu4jxrsa,nvyd2rotrraelcuchnu6cjbxty,Status.STRONG,PMID_DOI_PAIR qqsdtxm5hjadta3jf7bgt3bnm4,fupvtkn7t5d5xohffx5bt4yn24,Status.AMBIGUOUS, -6kuxfopbcjcrdnhvfokjgbd5wm,c43itb7esjc3heb64xbohigqge,Status.STRONG,OK.VERSIONED_DOI -jbodjm2njjdmhknlgxnicefwru,trdosozt55cndbnsfmcm46xckm,Status.STRONG,OK.VERSIONED_DOI +6kuxfopbcjcrdnhvfokjgbd5wm,c43itb7esjc3heb64xbohigqge,Status.STRONG,VERSIONED_DOI +jbodjm2njjdmhknlgxnicefwru,trdosozt55cndbnsfmcm46xckm,Status.STRONG,VERSIONED_DOI 6gnyb4zr25fodcooyfpyfd75bi,wt2qhxiz75bhfjgrq36376huyq,Status.AMBIGUOUS, -eaypmw4g2zbave557q3bfxstsu,pmr3siuyx5hzngoi4ve4mptxxu,Status.STRONG,OK.SLUG_TITLE_AUTHOR_MATCH +eaypmw4g2zbave557q3bfxstsu,pmr3siuyx5hzngoi4ve4mptxxu,Status.STRONG,SLUG_TITLE_AUTHOR_MATCH -- cgit v1.2.3