Feat/merge ignored nounphrases lists (#118)

* feat: merge ignored nounphrases

* fix: codestyle

* move ignore lists to separate dir and expose constants in init

* fix codestyle

* add docstring

* add ./common mount to spacy-nounphrases config

* feat: common for spacy-nounphrases

* fix: import

Co-authored-by: mtalimanchuk <mtalimanchuk@gmail.com>

annotators/fact_retrieval/tfidf_ranker.py

@@ -24,7 +24,8 @@
 from deeppavlov.core.models.estimator import Component
 from deeppavlov.core.common.file import read_json
 from deeppavlov.core.commands.utils import expand_path
-from remove_lists import NP_REMOVE_LIST, NP_IGNORE_LIST
+
+from common.ignore_lists import FALSE_POS_NPS_LIST, BAD_NPS_LIST
 
 logger = getLogger(__name__)
 
@@ -50,10 +51,10 @@ def __init__(
             freq_unigrams = f.read().splitlines()[:1000]
 
         self.np_ignore_expr = re.compile(
-            "(" + "|".join([r"\b%s\b" % word for word in NP_IGNORE_LIST + freq_unigrams]) + ")", re.IGNORECASE
+            "(" + "|".join([r"\b%s\b" % word for word in BAD_NPS_LIST + freq_unigrams]) + ")", re.IGNORECASE
         )
         self.np_remove_expr = re.compile(
-            "(" + "|".join([r"\b%s\b" % word for word in NP_REMOVE_LIST]) + ")", re.IGNORECASE
+            "(" + "|".join([r"\b%s\b" % word for word in FALSE_POS_NPS_LIST]) + ")", re.IGNORECASE
         )
         self.rm_spaces_expr = re.compile(r"\s\s+")
 

annotators/spacy_nounphrases/Dockerfile

@@ -1,10 +1,14 @@
 FROM python:3.8.4
 
 RUN mkdir /src
-COPY ./requirements.txt /src/requirements.txt
+
+COPY ./annotators/spacy_nounphrases/ /src/
+COPY ./common/ /src/common/
+
+COPY ./annotators/spacy_nounphrases/requirements.txt /src/requirements.txt
 RUN pip install -r /src/requirements.txt
 RUN pip install https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.2.0/en_core_web_sm-2.2.0.tar.gz
-COPY ./ /src/
+
 WORKDIR /src
 
 CMD gunicorn --workers=2 server:app