diff options
author | Martin Czygan <martin.czygan@gmail.com> | 2020-12-17 19:36:25 +0100 |
---|---|---|
committer | Martin Czygan <martin.czygan@gmail.com> | 2020-12-17 19:36:25 +0100 |
commit | 34ab8083fefbddcea314a60ea3ca7d4c2c0d01ec (patch) | |
tree | 3f230b7c22c444117969e73a069118571852322f | |
parent | 1816f807c2ed6e81985db78aa6b7589111fb6c33 (diff) | |
download | fuzzycat-34ab8083fefbddcea314a60ea3ca7d4c2c0d01ec.tar.gz fuzzycat-34ab8083fefbddcea314a60ea3ca7d4c2c0d01ec.zip |
update notes
-rw-r--r-- | fuzzycat/common.py | 4 | ||||
-rw-r--r-- | fuzzycat/matching.py | 1 | ||||
-rw-r--r-- | fuzzycat/verify.py | 2 |
3 files changed, 6 insertions, 1 deletions
diff --git a/fuzzycat/common.py b/fuzzycat/common.py index 9ee1239..142cb69 100644 --- a/fuzzycat/common.py +++ b/fuzzycat/common.py @@ -5,13 +5,15 @@ class Status(str, Enum): """ Match status. The match status "TODO" is a placeholder, e.g. to trigger a test failure. + + TODO: FuzzyStatus, FuzzycatStatus, MatchVerifyStatus, MatchConfidence """ AMBIGUOUS = 'ambiguous' DIFFERENT = 'different' EXACT = 'exact' STRONG = 'strong' WEAK = 'weak' - TODO = 'todo' + TODO = 'todo' # maybe UNIMPLEMENTED class Reason(str, Enum): diff --git a/fuzzycat/matching.py b/fuzzycat/matching.py index d840059..c9320e0 100644 --- a/fuzzycat/matching.py +++ b/fuzzycat/matching.py @@ -33,6 +33,7 @@ def match_release_fuzzy( es = elasticsearch.Elasticsearch() # Try to match by external identifier. + # TODO: use api, ability to disable; benchmark ext_ids = release.ext_ids attrs = { "doi": "doi", diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py index 7c1e462..260dca5 100644 --- a/fuzzycat/verify.py +++ b/fuzzycat/verify.py @@ -154,6 +154,8 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]: The cases are relatively independent, so order should not matter, but that can be pinned down much more clearly. + + TODO: add wrapper release entities """ # A few items have the same DOI. |