Added rule_list spacy registered function

CHANGELOG.md

@@ -39,6 +39,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - spaCy registered functions for reading in a `LexiconCollection` or `MWELexiconCollection` from a TSV. These can be found in `pymusas.spacy_api.lexicon_collection`.
 - spaCy registered functions for creating `SingleWordRule` and `MWERule`. These can be found in `pymusas.spacy_api.taggers.rules`.
 - spaCy registered function for creating `ContextualRuleBasedRanker`. This can be found in `pymusas.spacy_api.rankers`.
+- spaCy registered function for creating a `List` of `Rule`s, this can be found here: `pymusas.spacy_api.taggers.rules.rule_list`.
+- `LexiconCollection` and `MWELexiconCollection` open the TSV file downloaded through `from_tsv` method by default using `utf-8` encoding.
 
 ### Removed
 

docs/docs/api/spacy_api/lexicon_collection.md

@@ -18,7 +18,7 @@ spaCy registered functions for reading in a
 @spacy.util.registry.readers('pymusas.LexiconCollection.from_tsv')
 def lexicon_collection_from_tsv(
     tsv_file_path: Union[PathLike, str],
-    include_pos: bool
+    include_pos: bool = True
 ) -> Dict[str, List[str]]
 ```
 
@@ -39,7 +39,7 @@ dictionary object that can be used to create a
     3. `pos` (Optional)
 
     All other fields will be ignored.
-- __include\_pos__ : `bool` <br/>
+- __include\_pos__ : `bool`, optional (default = `True`) <br/>
     Whether to include the POS information, if the information is avaliable,
     or not. See [`add_lexicon_entry`](#add_lexicon_entry) for more information on this
     parameter.

docs/docs/api/spacy_api/taggers/rules.md

@@ -10,6 +10,8 @@ spaCy registered functions for creating the following tagger rules:
 * [`pymusas.taggers.rules.single_word.SingleWordRule`](/pymusas/api/taggers/rules/single_word/#singlewordrule)
 * [`pymusas.taggers.rules.mwe.MWERule`](/pymusas/api/taggers/rules/mwe/#mwerule)
 
+And helper functions for the rules.
+
 <a id="pymusas.spacy_api.taggers.rules.single_word_rule"></a>
 
 ### single\_word\_rule
@@ -19,7 +21,7 @@ spaCy registered functions for creating the following tagger rules:
 def single_word_rule(
     lexicon_collection: Dict[str, List[str]],
     lemma_lexicon_collection: Dict[str, List[str]],
-    pos_mapper: Dict[str, List[str]]
+    pos_mapper: Optional[Dict[str, List[str]]] = None
 ) -> SingleWordRule
 ```
 
@@ -42,7 +44,7 @@ details on parameters to this function.
 @spacy.util.registry.misc('pymusas.taggers.rules.MWERule.v1')
 def mwe_rule(
     mwe_lexicon_lookup: Dict[str, List[str]],
-    pos_mapper: Dict[str, List[str]]
+    pos_mapper: Optional[Dict[str, List[str]]] = None
 ) -> MWERule
 ```
 
@@ -57,3 +59,37 @@ parameters to this function.
 
 - [`pymusas.taggers.rules.mwe.MWERule`](/pymusas/api/taggers/rules/mwe/#mwerule) <br/>
 
+<a id="pymusas.spacy_api.taggers.rules.rule_list"></a>
+
+### rule\_list
+
+```python
+@spacy.util.registry.misc('pymusas.taggers.rules.rule_list')
+def rule_list(*rules: Rule) -> List[Rule]
+```
+
+`pymusas.taggers.rules.rule_list` is a registered function under the
+`@misc` function register. The function is required when wanting to create
+a `List` of rules within a
+[config file](https://thinc.ai/docs/usage-config). We
+found it not possible to specify a `List` of custom objects within a config
+file, but is possible when using
+[variable position arguments](https://thinc.ai/docs/usage-config#registries-args),
+which this function accepts as input.
+
+This function is most likely to be
+used when creating a [`pymusas.spacy_api.taggers.rule_based.RuleBasedTagger`](/pymusas/api/spacy_api/taggers/rule_based/#rulebasedtagger).
+
+
+<h4 id="rule_list.parameters">Parameters<a className="headerlink" href="#rule_list.parameters" title="Permanent link">&para;</a></h4>
+
+
+- __rules__ : `Rule` <br/>
+    The [`pymusas.taggers.rules.rule.Rule`](/pymusas/api/taggers/rules/rule/#rule)s to convert into a `List`
+    of `Rule`s.
+
+<h4 id="rule_list.returns">Returns<a className="headerlink" href="#rule_list.returns" title="Permanent link">&para;</a></h4>
+
+
+- `List[Rule]` <br/>
+

pymusas/spacy_api/lexicon_collection.py

@@ -14,7 +14,7 @@
 
 @spacy.util.registry.readers('pymusas.LexiconCollection.from_tsv')
 def lexicon_collection_from_tsv(tsv_file_path: Union[PathLike, str],
-                                include_pos: bool
+                                include_pos: bool = True
                                 ) -> Dict[str, List[str]]:
     '''
     `pymusas.LexiconCollection.from_tsv` is a registered function under the
@@ -33,7 +33,7 @@ def lexicon_collection_from_tsv(tsv_file_path: Union[PathLike, str],
         3. `pos` (Optional)
         
         All other fields will be ignored.
-    include_pos: `bool`
+    include_pos: `bool`, optional (default = `True`)
         Whether to include the POS information, if the information is avaliable,
         or not. See :func:`add_lexicon_entry` for more information on this
         parameter.

pymusas/spacy_api/taggers/rules.py

@@ -2,19 +2,23 @@
 spaCy registered functions for creating the following tagger rules:
 * :class:`pymusas.taggers.rules.single_word.SingleWordRule`
 * :class:`pymusas.taggers.rules.mwe.MWERule`
+
+And helper functions for the rules.
 '''
-from typing import Dict, List
+from typing import Dict, List, Optional
 
 import spacy
 
 from pymusas.taggers.rules.mwe import MWERule
 from pymusas.taggers.rules.single_word import SingleWordRule
+from pymusas.taggers.rules.rule import Rule
 
 
 @spacy.util.registry.misc('pymusas.taggers.rules.SingleWordRule.v1')
 def single_word_rule(lexicon_collection: Dict[str, List[str]],
                      lemma_lexicon_collection: Dict[str, List[str]],
-                     pos_mapper: Dict[str, List[str]]) -> SingleWordRule:
+                     pos_mapper: Optional[Dict[str, List[str]]] = None
+                     ) -> SingleWordRule:
     '''
     `pymusas.taggers.rules.SingleWordRule.v1` is a registered function under the
     `@misc` function register.
@@ -32,7 +36,8 @@ def single_word_rule(lexicon_collection: Dict[str, List[str]],
 
 @spacy.util.registry.misc('pymusas.taggers.rules.MWERule.v1')
 def mwe_rule(mwe_lexicon_lookup: Dict[str, List[str]],
-             pos_mapper: Dict[str, List[str]]) -> MWERule:
+             pos_mapper: Optional[Dict[str, List[str]]] = None
+             ) -> MWERule:
     '''
     `pymusas.taggers.rules.MWERule.v1` is a registered function under the
     `@misc` function register.
@@ -45,3 +50,32 @@ def mwe_rule(mwe_lexicon_lookup: Dict[str, List[str]],
     :class:`pymusas.taggers.rules.mwe.MWERule`
     '''
     return MWERule(mwe_lexicon_lookup, pos_mapper)
+
+
+@spacy.util.registry.misc('pymusas.taggers.rules.rule_list')
+def rule_list(*rules: Rule) -> List[Rule]:
+    '''
+    `pymusas.taggers.rules.rule_list` is a registered function under the
+    `@misc` function register. The function is required when wanting to create
+    a `List` of rules within a
+    [config file](https://thinc.ai/docs/usage-config). We
+    found it not possible to specify a `List` of custom objects within a config
+    file, but is possible when using
+    [variable position arguments](https://thinc.ai/docs/usage-config#registries-args),
+    which this function accepts as input.
+    
+    This function is most likely to be
+    used when creating a :class:`pymusas.spacy_api.taggers.rule_based.RuleBasedTagger`.
+
+
+    # Parameters
+    
+    rules : `Rule`
+        The :class:`pymusas.taggers.rules.rule.Rule`s to convert into a `List`
+        of `Rule`s.
+    
+    # Returns
+    
+    `List[Rule]`
+    '''
+    return list(rules)

tests/spacy_api/taggers/test_spacy_api_rules.py

@@ -3,6 +3,7 @@
 import spacy
 
 from pymusas.spacy_api.taggers import rules  # noqa: F401
+from pymusas.taggers.rules.rule import Rule
 from pymusas.taggers.rules.mwe import MWERule
 from pymusas.taggers.rules.single_word import SingleWordRule
 
@@ -18,3 +19,13 @@ def test_mwe_rule() -> None:
     mwe_rule: Callable[[Dict[str, List[str]], Dict[str, List[str]]], MWERule] \
         = spacy.util.registry.misc.get('pymusas.taggers.rules.MWERule.v1')
     assert isinstance(mwe_rule({}, {}), MWERule)
+
+
+def test_rule_list() -> None:
+    rule_list_call: Callable[[Rule, Rule], List[Rule]] \
+        = spacy.util.registry.misc.get('pymusas.taggers.rules.rule_list')
+    single_rule = SingleWordRule({}, {})
+    mwe_rule = MWERule({})
+    list_of_rules = rule_list_call(*(single_rule, mwe_rule))
+    assert isinstance(list_of_rules, List)
+    assert [single_rule, mwe_rule] == list_of_rules