diff options
| -rw-r--r-- | docs/known_issues.md | 15 | ||||
| -rw-r--r-- | fuzzycat/__main__.py | 41 | ||||
| -rw-r--r-- | fuzzycat/utils.py | 34 | ||||
| -rw-r--r-- | fuzzycat/verify.py | 98 | ||||
| -rw-r--r-- | tests/data/verify.csv | 2 | ||||
| -rw-r--r-- | tests/test_utils.py | 2 |
6 files changed, 142 insertions, 50 deletions
diff --git a/docs/known_issues.md b/docs/known_issues.md new file mode 100644 index 0000000..662130c --- /dev/null +++ b/docs/known_issues.md @@ -0,0 +1,15 @@ +# Known issues + +Both the clustering and verification stage are not perfect. Here, some known +cases are documented. + +# Clustering + +# Verification + +## A new approach to fault-tolerant wormhole routing for mesh-connected parallel computers + +* https://fatcat.wiki/release/izaz6gjnfzhgnaetizf4bt2r24 +* https://fatcat.wiki/release/vwfepcqcdzfwjnsoym7o5o75yu + + diff --git a/fuzzycat/__main__.py b/fuzzycat/__main__.py index b2c8e60..89e3a12 100644 --- a/fuzzycat/__main__.py +++ b/fuzzycat/__main__.py @@ -17,13 +17,20 @@ import io import json import logging import pstats +import random import sys import tempfile +import requests + from fuzzycat.cluster import (Cluster, release_key_title, release_key_title_ngram, release_key_title_normalized, release_key_title_nysiis, release_key_title_sandcrawler) -from fuzzycat.verify import GroupVerifier +from fuzzycat.utils import random_word +from fuzzycat.verify import GroupVerifier, verify + +logging.getLogger("requests").setLevel(logging.WARNING) +logging.getLogger("urllib3").setLevel(logging.WARNING) def run_cluster(args): @@ -57,6 +64,31 @@ def run_verify(args): gv.run() +def run_verify_single(args): + """ + Run a single verification on a pair. + """ + result = {} + if args.a and args.b: + a, b = args.a, args.b + elif not args.a and not args.b: + word = random_word(wordsfile='/usr/share/dict/words') + a, b = random_idents_from_query(query=word, r=2) + result.update({"extra": {"q": "https://fatcat.wiki/release/search?q={}".format(word)}}) + else: + raise ValueError('specify either both -a, -b or none') + + def fetch_ident(ident): + return requests.get("https://api.fatcat.wiki/v0/release/{}".format(ident)).json() + + result.update({ + "a": "https://fatcat.wiki/release/{}".format(a), + "b": "https://fatcat.wiki/release/{}".format(b), + "r": verify(fetch_ident(a), fetch_ident(b)), + }) + print(json.dumps(result)) + + if __name__ == '__main__': logging.basicConfig( level=logging.DEBUG, @@ -91,6 +123,13 @@ if __name__ == '__main__': sub_verify.add_argument('-f', '--files', default="-", help='input files') sub_verify.set_defaults(func=run_verify) + sub_verify_single = subparsers.add_parser('verify-single', + help='verify a single pair', + parents=[parser]) + sub_verify_single.add_argument('-a', help='ident or url to release') + sub_verify_single.add_argument('-b', help='ident or url to release') + sub_verify_single.set_defaults(func=run_verify_single) + args = parser.parse_args() if not args.__dict__.get("func"): print(__doc__, file=sys.stderr) diff --git a/fuzzycat/utils.py b/fuzzycat/utils.py index 682f912..cf74220 100644 --- a/fuzzycat/utils.py +++ b/fuzzycat/utils.py @@ -1,6 +1,8 @@ import collections import io import itertools +import os +import random import re import string @@ -13,6 +15,7 @@ CHEM_FORMULA = re.compile(r"([A-Z]{1,2}[0-9]{1,2})+") ParsedPages = collections.namedtuple("ParsedPages", "start end count") + def parse_page_string(s): """ Parse typical page strings, e.g. 150-180. @@ -35,6 +38,7 @@ def parse_page_string(s): count = b - a + 1 return ParsedPages(start=a, end=b, count=count) + def dict_key_exists(doc, path): """ Return true, if key in a dictionary at a given path exists. XXX: probably @@ -138,3 +142,33 @@ def contains_chemical_formula(s): for token in s.split(): if CHEM_FORMULA.search(token): return True + + +def random_word(func=lambda w: True, wordsfile='/usr/share/dict/words'): + """ + Requires the UNIX words file in a typical location. Returns a single, + random word. + """ + if not os.path.exists(wordsfile): + raise RuntimeError('file not found: {}'.format(wordsfile)) + with open(wordsfile) as f: + words = list(filter(func, (word.strip() for word in f))) + return random.choice(words) + + +def random_idents_from_query(query="*", + es="https://search.fatcat.wiki/fatcat_release/_search", + max_retries=10, + r=2): + """ + Return a number of random idents from a search query. + """ + for _ in range(max_retries): + r = requests.get(es, params={"q": query}) + if r.status_code != 200: + raise RuntimeError('could not query {} for random item: {}'.format(es, r.url)) + resp = r.json() + if resp["hits"]["total"] < 2: + continue + idents = [doc["_source"]["ident"] for doc in resp["hits"]["hits"]] + return random.sample(idents, r) diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py index 93b9f1d..7f44f39 100644 --- a/fuzzycat/verify.py +++ b/fuzzycat/verify.py @@ -90,7 +90,9 @@ from fuzzycat.common import Reason, Status 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, - has_doi_prefix, jaccard, num_project, slugify_string, parse_page_string) + has_doi_prefix, jaccard, num_project, parse_page_string, slugify_string) + +Verify = collections.namedtuple("Verify", "status reason") class GroupVerifier: @@ -163,13 +165,13 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: # A few items have the same DOI. try: if glom(a, "ext_ids.doi") == glom(b, "ext_ids.doi"): - return (Status.EXACT, Reason.DOI) + return Verify(Status.EXACT, Reason.DOI) except PathAccessError: pass # Some pre-verified pairs. if a.get("work_id") and a.get("work_id") == b.get("work_id"): - return (Status.EXACT, Reason.WORK_ID) + return Verify(Status.EXACT, Reason.WORK_ID) a_title = a.get("title", "") or "" a_title_lower = a_title.lower() @@ -180,19 +182,19 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: assert isinstance(b_title, str) if len(a_title) < min_title_length: - return (Status.AMBIGUOUS, Reason.SHORT_TITLE) + return Verify(Status.AMBIGUOUS, Reason.SHORT_TITLE) if a_title_lower in TITLE_BLACKLIST: - return (Status.AMBIGUOUS, Reason.BLACKLISTED) + return Verify(Status.AMBIGUOUS, Reason.BLACKLISTED) for fragment in TITLE_FRAGMENT_BLACKLIST: if fragment in a_title_lower: - return (Status.AMBIGUOUS, Reason.BLACKLISTED_FRAGMENT) + return Verify(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, Reason.CONTAINER) + return Verify(Status.DIFFERENT, Reason.CONTAINER) except PathAccessError: pass @@ -200,7 +202,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: try: if a_title and a_title == b_title and glom(a, "extra.datacite.metadataVersion") != glom( b, "extra.datacite.metadataVersion"): - return (Status.EXACT, Reason.DATACITE_VERSION) + return Verify(Status.EXACT, Reason.DATACITE_VERSION) except PathAccessError: pass @@ -214,7 +216,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: # 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, Reason.CUSTOM_PREFIX_10_14288) + return Verify(Status.DIFFERENT, Reason.CUSTOM_PREFIX_10_14288) except PathAccessError: pass @@ -228,12 +230,12 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.CUSTOM_BSI_UNDATED) + return Verify(Status.STRONG, Reason.CUSTOM_BSI_UNDATED) if a_title == b_title and ((dict_key_exists(a, "extra.subtitle") 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, Reason.CUSTOM_BSI_SUBDOC) + return Verify(Status.STRONG, Reason.CUSTOM_BSI_SUBDOC) except PathAccessError: pass @@ -246,16 +248,16 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: v = "{}/ma".format(prefix) if (a_doi.startswith(v) and not b_doi.startswith(v) or b_doi.startswith(v) and not a_doi.startswith(v)): - return (Status.DIFFERENT, Reason.CUSTOM_IOP_MA_PATTERN) + return Verify(Status.DIFFERENT, Reason.CUSTOM_IOP_MA_PATTERN) except PathAccessError: pass # Very manual, XXX: move this into blacklist. if "Zweckverband Volkshochschule " in a_title and a_title != b_title: - return (Status.DIFFERENT, Reason.CUSTOM_VHS) + return Verify(Status.DIFFERENT, Reason.CUSTOM_VHS) if re.match(r"appendix ?[^ ]*$", a_title_lower): - return (Status.AMBIGUOUS, Reason.APPENDIX) + return Verify(Status.AMBIGUOUS, Reason.APPENDIX) # Figshare, versions. try: @@ -265,7 +267,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: a_doi_v_stripped = re.sub(r"[.]v[0-9]+$", "", glom(a, "ext_ids.doi")) b_doi_v_stripped = re.sub(r"[.]v[0-9]+$", "", glom(b, "ext_ids.doi")) if a_doi_v_stripped == b_doi_v_stripped: - return (Status.STRONG, Reason.FIGSHARE_VERSION) + return Verify(Status.STRONG, Reason.FIGSHARE_VERSION) except PathAccessError: pass @@ -277,7 +279,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: b_doi = glom(b, "ext_ids.doi") versioned_doi_pattern = '10[.].*/v[0-9]{1,}$' if re.match(versioned_doi_pattern, a_doi) and re.match(versioned_doi_pattern, b_doi): - return (Status.STRONG, Reason.VERSIONED_DOI) + return Verify(Status.STRONG, Reason.VERSIONED_DOI) except PathAccessError: pass @@ -288,7 +290,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.VERSIONED_DOI) + return Verify(Status.STRONG, Reason.VERSIONED_DOI) except PathAccessError: pass @@ -321,7 +323,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.DATACITE_RELATED_ID) + return Verify(Status.STRONG, Reason.DATACITE_RELATED_ID) except PathAccessError: pass @@ -330,7 +332,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.ARXIV_VERSION) + return Verify(Status.STRONG, Reason.ARXIV_VERSION) except (AttributeError, ValueError, PathAccessError) as exc: pass @@ -351,11 +353,11 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: "paper-conference", ]) if len(types & ignore_release_types) == 0: - return (Status.DIFFERENT, Reason.RELEASE_TYPE) + return Verify(Status.DIFFERENT, Reason.RELEASE_TYPE) if "dataset" in types and ("article" in types or "article-journal" in types): - return (Status.DIFFERENT, Reason.RELEASE_TYPE) + return Verify(Status.DIFFERENT, Reason.RELEASE_TYPE) if "book" in types and ("article" in types or "article-journal" in types): - return (Status.DIFFERENT, Reason.RELEASE_TYPE) + return Verify(Status.DIFFERENT, Reason.RELEASE_TYPE) except PathAccessError: pass @@ -363,7 +365,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.DATASET_DOI) + return Verify(Status.DIFFERENT, Reason.DATASET_DOI) except PathAccessError: pass @@ -371,14 +373,14 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.BOOK_CHAPTER) + return Verify(Status.DIFFERENT, Reason.BOOK_CHAPTER) except PathAccessError: pass # Components tend to have similar names. try: if glom(a, "extra.crossref.type") == "component" and glom(a, "title") != glom(b, "title"): - return (Status.DIFFERENT, Reason.COMPONENT) + return Verify(Status.DIFFERENT, Reason.COMPONENT) except PathAccessError: pass @@ -387,7 +389,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: a_doi = glom(a, "ext_ids.doi") b_doi = glom(b, "ext_ids.doi") if a_doi != b_doi: - return (Status.DIFFERENT, Reason.COMPONENT) + return Verify(Status.DIFFERENT, Reason.COMPONENT) except PathAccessError: pass @@ -401,7 +403,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.YEAR) + return Verify(Status.DIFFERENT, Reason.YEAR) if a_slug_title == b_slug_title: # via: https://fatcat.wiki/release/ij3yuoh6lrh3tkrv5o7gfk6yyi @@ -410,7 +412,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: try: if (glom(a, "ext_ids.doi").split("/")[0] == "10.1109" and glom(b, "ext_ids.arxiv") != ""): - return (Status.STRONG, Reason.CUSTOM_IEEE_ARXIV) + return Verify(Status.STRONG, Reason.CUSTOM_IEEE_ARXIV) except PathAccessError: pass @@ -430,7 +432,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.CUSTOM_PREFIX_10_7916) + return Verify(Status.AMBIGUOUS, Reason.CUSTOM_PREFIX_10_7916) except PathAccessError: pass @@ -441,7 +443,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: for a_sub in a_subtitles: for b_sub in b_subtitles: if slugify_string(a_sub) != slugify_string(b_sub): - return (Status.DIFFERENT, Reason.SUBTITLE) + return Verify(Status.DIFFERENT, Reason.SUBTITLE) except PathAccessError: pass @@ -463,54 +465,54 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: # 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, Reason.YEAR) - return (Status.EXACT, Reason.TITLE_AUTHOR_MATCH) + return Verify(Status.DIFFERENT, Reason.YEAR) + return Verify(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, Reason.TITLE_FILENAME) + return Verify(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, Reason.YEAR) + return Verify(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, Reason.CHEM_FORMULA) + return Verify(Status.DIFFERENT, Reason.CHEM_FORMULA) if len(a_slug_title) < 10 and a_slug_title != b_slug_title: - return (Status.AMBIGUOUS, Reason.SHORT_TITLE) + return Verify(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, Reason.NUM_DIFF) + return Verify(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, Reason.PREPRINT_PUBLISHED) + return Verify(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, Reason.SLUG_TITLE_AUTHOR_MATCH) + return Verify(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, Reason.PMID_DOI_PAIR) + return Verify(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, Reason.JSTOR_ID) + return Verify(Status.DIFFERENT, Reason.JSTOR_ID) except PathAccessError: pass @@ -524,7 +526,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: if a_container_id == b_container_id and a_doi != b_doi and not has_doi_prefix( a_doi, "10.1126"): - return (Status.DIFFERENT, Reason.SHARED_DOI_PREFIX) + return Verify(Status.DIFFERENT, Reason.SHARED_DOI_PREFIX) except PathAccessError: pass @@ -549,7 +551,7 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: if len(top_scores) > 0: avg_score = sum(top_scores) / len(top_scores) if avg_score > 0.5: - return (Status.STRONG, Reason.TOKENIZED_AUTHORS) + return Verify(Status.STRONG, Reason.TOKENIZED_AUTHORS) else: pass # Kuidong Xu, Joong Ki Choi, Eun Jin Yang, Kyu Chul Lee, Yanli Lei @@ -564,19 +566,19 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: 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, Reason.JACCARD_AUTHORS) + return Verify(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, Reason.CONTRIB_INTERSECTION_EMPTY) + return Verify(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, Reason.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW) + return Verify(Status.AMBIGUOUS, Reason.CUSTOM_PREFIX_10_5860_CHOICE_REVIEW) except PathAccessError: pass @@ -587,8 +589,8 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: a_parsed_pages = parse_page_string(glom(a, "pages")) b_parsed_pages = parse_page_string(glom(b, "pages")) if abs(a_parsed_pages.count - b_parsed_pages.count) > 5: - return (Status.DIFFERENT, Reason.PAGE_COUNT) + return Verify(Status.DIFFERENT, Reason.PAGE_COUNT) except (ValueError, PathAccessError): pass - return (Status.AMBIGUOUS, Reason.DUMMY) + return Verify(Status.AMBIGUOUS, Reason.DUMMY) diff --git a/tests/data/verify.csv b/tests/data/verify.csv index e594223..74109ba 100644 --- a/tests/data/verify.csv +++ b/tests/data/verify.csv @@ -175,4 +175,4 @@ drzpue5r6zajlpa3fkyjdetuqy,fppfjl5kt5dsnfl2i5rarhqaaq,Status.DIFFERENT,CONTRIB_I drzpue5r6zajlpa3fkyjdetuqy,zqqbuha3uzd2fcvekdy3ygxnni,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY fppfjl5kt5dsnfl2i5rarhqaaq,zqqbuha3uzd2fcvekdy3ygxnni,Status.DIFFERENT,CONTRIB_INTERSECTION_EMPTY 36e4mmbnlfg5tm5pz4zrokbxde,oxptehhpj5aihk2l42alqg55he,Status.EXACT,TITLE_AUTHOR_MATCH -2t5mhzgf6vbirgjxmegaemyoqm,rj3fg7sudbbc5hgx5riruivhbm,Status.AMBIGUOUS,DUMMY +2t5mhzgf6vbirgjxmegaemyoqm,rj3fg7sudbbc5hgx5riruivhbm,Status.AMBIGUOUS, diff --git a/tests/test_utils.py b/tests/test_utils.py index 38d50a7..fa930fe 100644 --- a/tests/test_utils.py +++ b/tests/test_utils.py @@ -64,6 +64,7 @@ def test_nwise(): assert list(nwise("1234", n=1)) == [("1", ), ("2", ), ("3", ), ("4", )] assert list(nwise([1, 2, 3, 4, 5], n=3)) == [(1, 2, 3), (4, 5)] + def test_dict_key_exists(): assert dict_key_exists({}, "") is False assert dict_key_exists({"a": "a"}, "a") == True @@ -72,6 +73,7 @@ def test_dict_key_exists(): assert dict_key_exists({"a": {"b": None}}, "a.b") == True assert dict_key_exists({"a": {"b": "c"}}, "a.b.c") == False + def test_page_page_string(): reject = ("", "123-2", "123-120", "123a-124", "-2-1") for s in reject: |