Merge pull request #79 from vmenger/update-dependencies

Update dependencies

Author: vmenger

CHANGELOG.md

@@ -5,6 +5,11 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## 2.0.2 (2023-03-28)
+
+### Changed
+- upgraded dependencies, including `markdown-it-py` which had a vulnerability
+
 ## 2.0.1 (2022-12-09)
 
 ### Changed

CONTRIBUTING.md

@@ -33,6 +33,6 @@ Before starting, some things to consider:
 ## Releasing
 * Readthedocs has a webhook connected to pushes on the main branch. It will trigger and update automatically. 
 * Create a [release on github](https://github.com/vmenger/docdeid/releases/new), create a tag with the right version, manually copy and paste from the changelog
-* Trigger the build pipeline manually to release to PyPi
+* Build pipeline and release to PyPi trigger automatically on release
 
 Any other questions/issues not covered here? Please just get in touch!

deduce/backwards_compat.py

@@ -15,7 +15,6 @@
 
 
 class _BackwardsCompat:
-
     deduce_model = None
 
     @classmethod

deduce/deduce.py

@@ -116,7 +116,6 @@ class _AnnotatorFactory:
     """Responsible for creating annotators, based on config."""
 
     def __init__(self) -> None:
-
         self.annotator_creators = {
             "token_pattern": self._get_token_pattern_annotator,
             "annotation_context": self._get_annotation_context_pattern_annotator,

deduce/pattern/name.py

@@ -16,11 +16,9 @@ class PrefixWithNamePattern(TokenPatternWithLookup):
     """Matches prefixes followed by a titlecase word."""
 
     def token_precondition(self, token: dd.Token) -> bool:
-
         return token.next() is not None
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if (
             token.text.lower() in self._lookup_sets["prefixes"]
             and token.next().text[0].isupper()
@@ -36,11 +34,9 @@ class InterfixWithNamePattern(TokenPatternWithLookup):
     """Matches interfixes followed by an interfix surname."""
 
     def token_precondition(self, token: dd.Token) -> bool:
-
         return token.next() is not None
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if (
             token.text.lower() in self._lookup_sets["interfixes"]
             and token.next().text in self._lookup_sets["interfix_surnames"]
@@ -56,11 +52,9 @@ class InitialWithCapitalPattern(TokenPatternWithLookup):
     """Matches an initial followed by an titlecase word with at least 3 characters."""
 
     def token_precondition(self, token: dd.Token) -> bool:
-
         return token.next() is not None
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if (
             token.text[0].isupper()
             and len(token) == 1
@@ -78,7 +72,6 @@ class InitiaalInterfixCapitalPattern(TokenPatternWithLookup):
     """Matches an initial, followed by an interfix, followed by a titlecase word."""
 
     def token_precondition(self, token: dd.Token) -> bool:
-
         return (token.previous() is not None) and (token.next() is not None)
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
@@ -98,7 +91,6 @@ class FirstNameLookupPattern(TokenPatternWithLookup):
     """Matches first names, based on lookup."""
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if token.text in self._lookup_sets["first_names"] and token.text not in self._lookup_sets["whitelist"]:
 
             return token, token
@@ -110,7 +102,6 @@ class SurnameLookupPattern(TokenPatternWithLookup):
     """Matches surnames, based on lookup."""
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if token.text in self._lookup_sets["surnames"] and token.text not in self._lookup_sets["whitelist"]:
 
             return token, token

deduce/pattern/name_context.py

@@ -45,11 +45,9 @@ class InterfixContextPattern(AnnotationContextPatternWithLookupSet):
     """Matches an annotated name or initial, followed by an interfix, followed by a titlecase word."""
 
     def annotation_precondition(self, annotation: dd.Annotation) -> bool:
-
         return annotation.end_token.next() is not None and annotation.end_token.next(2) is not None
 
     def match(self, annotation: dd.Annotation) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if (
             utils.any_in_text(["initia", "naam"], annotation.tag)
             and annotation.end_token.next().text in self._lookup_sets["interfixes"]
@@ -65,11 +63,9 @@ class InitialsContextPattern(AnnotationContextPatternWithLookupSet):
     """Matches an annotated achternaam, interfix or initial, preceded by either an initial or a titlecase word."""
 
     def annotation_precondition(self, annotation: dd.Annotation) -> bool:
-
         return annotation.start_token.previous() is not None
 
     def match(self, annotation: dd.Annotation) -> Optional[tuple[dd.Token, dd.Token]]:
-
         previous_token_is_initial = (
             len(annotation.start_token.previous().text) == 1 and annotation.start_token.previous().text[0].isupper()
         )
@@ -95,11 +91,9 @@ class InitialNameContextPattern(AnnotationContextPatternWithLookupSet):
     characters."""
 
     def annotation_precondition(self, annotation: dd.Annotation) -> bool:
-
         return annotation.end_token.next() is not None
 
     def match(self, annotation: dd.Annotation) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if (
             utils.any_in_text(["initia", "voornaam", "roepnaam", "prefix"], annotation.tag)
             and len(annotation.end_token.next().text) > 3
@@ -116,11 +110,9 @@ class NexusContextPattern(AnnotationContextPattern):
     """Matches any annotated name, followed by "en", followed by a titlecase word."""
 
     def annotation_precondition(self, annotation: dd.Annotation) -> bool:
-
         return annotation.end_token.next() is not None and annotation.end_token.next(2) is not None
 
     def match(self, annotation: dd.Annotation) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if annotation.end_token.next().text == "en" and annotation.end_token.next(2).text[0].isupper():
 
             return annotation.start_token, annotation.end_token.next(2)

deduce/pattern/name_patient.py

@@ -10,12 +10,10 @@ class PersonFirstNamePattern(dd.TokenPattern):
     metadata, with a max edit distance of 1."""
 
     def doc_precondition(self, doc: dd.Document) -> bool:
-
         patient = doc.metadata["patient"]
         return (patient is not None) and (patient.first_names is not None)
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         for first_name in metadata["patient"].first_names:
 
             if str_match(token.text, first_name) or (
@@ -36,12 +34,10 @@ class PersonInitialFromNamePattern(dd.TokenPattern):
     """
 
     def doc_precondition(self, doc: dd.Document) -> bool:
-
         patient = doc.metadata["patient"]
         return (patient is not None) and (patient.first_names is not None)
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         for _, first_name in enumerate(metadata["patient"].first_names):
 
             if str_match(token.text, first_name[0]):
@@ -60,12 +56,10 @@ class PersonInitialsPattern(dd.TokenPattern):
     """Matches the patients initials, as defined in the "patient" Person in the document metadata."""
 
     def doc_precondition(self, doc: dd.Document) -> bool:
-
         patient = doc.metadata["patient"]
         return (patient is not None) and (patient.initials is not None)
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         if str_match(token.text, metadata["patient"].initials):
             return token, token
 
@@ -85,7 +79,6 @@ def __init__(self, tokenizer: dd.Tokenizer, *args, **kwargs) -> None:
         super().__init__(*args, **kwargs)
 
     def doc_precondition(self, doc: dd.Document) -> bool:
-
         patient = doc.metadata["patient"]
 
         if (patient is None) or (patient.surname is None):
@@ -96,7 +89,6 @@ def doc_precondition(self, doc: dd.Document) -> bool:
         return True
 
     def match(self, token: dd.Token, metadata: dd.MetaData) -> Optional[tuple[dd.Token, dd.Token]]:
-
         surname_pattern = metadata["surname_pattern"]
         surname_token = surname_pattern[0]
         start_token = token

deduce/process/annotation_processing.py

@@ -67,7 +67,6 @@ def __init__(self) -> None:
         )
 
     def process_annotations(self, annotations: dd.AnnotationSet, text: str) -> dd.AnnotationSet:
-
         new_annotations = self._overlap_resolver.process_annotations(annotations, text=text)
 
         return dd.AnnotationSet(

deduce/process/annotator.py

@@ -107,7 +107,6 @@ def _annotate_context(self, annotations: list[dd.Annotation], doc: dd.Document)
         return next_annotations
 
     def annotate(self, doc: dd.Document) -> list[dd.Annotation]:
-
         context_annotations = self.get_matching_tag_annotations(list(doc.annotations))
         doc.annotations.difference_update(context_annotations)
 

deduce/process/redact.py

@@ -12,7 +12,6 @@ class DeduceRedactor(dd.process.SimpleRedactor):
     """
 
     def redact(self, text: str, annotations: dd.AnnotationSet) -> str:
-
         annotations_to_intext_replacement = {}
 
         for tag, annotation_group in self._group_annotations_by_tag(annotations).items():