Merge branch 'develop' into 'master'

Develop

See merge request !1

.gitlab-ci.yml

+image: 'clarinpl/python:3.6'
+cache:
+  paths:
+    - .tox
+stages:
+  - check_style
+  - build
+before_script:
+  - pip install tox==2.9.1
+pep8:
+  stage: check_style
+  script:
+    - tox -v -e pep8
+docstyle:
+  stage: check_style
+  script:
+    - tox -v -e docstyle
+build_image:
+  stage: build
+  image: 'docker:18.09.7'
+  only:
+    - master
+  services:
+    - 'docker:18.09.7-dind'
+  before_script:
+    - ''
+  script:
+    - docker build -t clarinpl/anonymizer .
+    - echo $DOCKER_PASSWORD > pass.txt
+    - cat pass.txt | docker login --username $DOCKER_USERNAME --password-stdin
+    - rm pass.txt
+    - docker push clarinpl/anonymizer

Dockerfile

+FROM clarinpl/python:3.6
+
+WORKDIR /home/worker
+COPY ./src ./src
+COPY ./main.py .
+COPY ./requirements.txt .
+
+RUN python3.6 -m pip install -r requirements.txt
+
+CMD ["python3.6", "main.py", "service"]

README.md

-# anonymizer
-
+# Anonymizer
+
+Liner2 should use model 5nam.
+tekst->any2txt->morphodita->liner2->anonymizer

config.ini

+[service]
+tool = anonymizer
+
+root = /samba/requests/
+rabbit_host = rabbitmq
+rabbit_user = test
+rabbit_password = test
+queue_prefix = nlp_
+
+[tool]
+workers_number = 1
+
+[logging]
+port = 9998
+local_log_level = INFO
+
+[logging_levels]
+__main__ = INFO
+

docker-compose.yml

+version: '3'
+services:
+  tokenizer:
+    container_name: clarin_anonymizer
+    build: ./
+    working_dir: /home/worker
+    entrypoint:
+      - python3.6
+      - main.py
+      - service
+    environment:
+      - PYTHONUNBUFFERED=0
+    volumes:
+      - '/samba:/samba'
+      - './config.ini:/home/worker/config.ini'
+      - './src:/home/worker/src'
+      - './main.py:/home/worker/main.py'
+      - './wiki.txt:/home/worker/wiki.txt'

main.py

+"""Implementation of anonymizer service."""
+import argparse
+import nlp_ws
+from src.worker import Worker
+
+
+def get_args():
+    """Gets command line arguments."""
+    parser = argparse.ArgumentParser(description="anonymizer")
+
+    subparsers = parser.add_subparsers(dest="mode")
+    subparsers.required = True
+
+    subparsers.add_parser(
+        "service",
+        help="Run as a service")
+
+    return parser.parse_args()
+
+
+def main():
+    """Runs the program."""
+    args = get_args()
+
+    generators = {
+        "service": lambda: nlp_ws.NLPService.main(Worker),
+    }
+
+    gen_fn = generators.get(args.mode, lambda: None)
+    gen_fn()
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

+nlp-ws
\ No newline at end of file

src/ccl_handler.py

+"""Implementation of ccl reading functionality."""
+from xml.etree.ElementTree import iterparse
+
+
+class Ccl_handler:
+    """Implements reading ccl for anonymizer service."""
+
+    def __init__(self, ccl_file_name):
+        """Initialize ccl_handler with a filename."""
+        self._file_name = ccl_file_name
+
+    def process(self, output_file, unmarshallers):
+        """Process xml tags using unmarshallers and save in output_file."""
+        with open(output_file, 'w', encoding='utf-8') as out:
+            with open(self._file_name, 'r', encoding='utf-8') as f:
+                for event, elem in iterparse(f):
+                    unmarshal = unmarshallers.get(elem.tag, None)
+                    if unmarshal:
+                        out.write(unmarshal(elem))
+                        elem.clear()

src/worker.py

+"""Implementation of nlp_worker."""
+import logging
+
+import nlp_ws
+
+
+from src.anonymizer import Anonymizer
+from src.ccl_handler import Ccl_handler
+
+_log = logging.getLogger(__name__)
+
+
+class Worker(nlp_ws.NLPWorker):
+    """Implements nlp_worker for anonymizer service."""
+
+    def process(self, input_file, task_options, output_file):
+        """Anonymizes input text.
+
+        It is assumed input_file is encoded in UTF-8.
+
+        Options:
+        method - 'delete'/'tag'/'pseudo' - 'delete' deletes selected tokens,
+                'tag' replaces selected tokens with arbitrary tags, 'pseudo'
+                replaces selected tokens with a random token that
+        """
+        anon = Anonymizer(task_options)
+        ccl_handler = Ccl_handler(input_file)
+        ccl_handler.process(output_file, anon.unmarshallers)

tox.ini

+[tox]
+envlist = pep8,docstyle
+skipsdist = True
+
+[testenv:pep8]
+deps =
+    flake8
+basepython = python3
+commands =
+    flake8 {posargs}
+
+[testenv:docstyle]
+deps =
+    pydocstyle
+basepython = python3
+commands =
+    pydocstyle --verbose {posargs}
+
+[flake8]
+# W504 skipped because it is overeager and unnecessary
+ignore = W504
+show-source = True
+exclude = .git,.venv,.tox,dist,doc,*egg,build,venv
+import-order-style = pep8
+max-line-length = 80
+
+
+[pydocstyle]
+# D104 Missing docstring in public package
+# D203 1 blank line required before class docstring
+# D213 Multi-line docstring summary should start at the second line
+# D214 Section is over-indented
+# D215 Section underline is over-indented
+# D401 First line should be in imperative mood; try rephrasing
+# D405 Section name should be properly capitalized
+# D406 Section name should end with a newline
+# D407 Missing dashed underline after section
+# D408 Section underline should be in the line following the section’s name
+# D409 Section underline should match the length of its name
+# D410 Missing blank line after section
+# D411 Missing blank line before section
+ignore = D104,D203,D213,D214,D215,D401,D405,D406,D407,D408,D409,D410,D411
+match-dir = ^(?!\.tox|venv).*
+match = ^(?!setup).*\.py
\ No newline at end of file

utility/NELex2_to_wiki.py

+"""Convert NELexicon into wiki used by anonymizer.
+
+Requires morfeusz2 to be installed.
+"""
+
+import morfeusz2
+morf = morfeusz2.Morfeusz(expand_tags=True)
+
+_file_to_liner_dispatch = {
+    'nam_liv_person': 'person_first_nam',
+    'nam_liv_person_last': 'person_last_nam',
+    'nam_fac_road': 'road_nam',
+    'nam_loc_gpe_city': 'city_nam',
+    'nam_org_group_team': 'country_nam'
+}
+
+_allowed_genders = ['f', 'm1', 'm2', 'm3', 'n']
+
+
+def _create_wiki():
+    with open('wiki.txt', 'wt+', encoding='utf-8') as f:
+        _add_gender(f)
+        _last_names(f)
+
+
+def _add_gender(
+        output,
+        file_name='nelexicon2/extra/wiktionary-forms-with-bases-and-tags.txt'
+):
+    with open(file_name, 'r', encoding='utf-8') as f:
+        _form_dict = dict()
+        for line in f:
+            l_list = line.split()
+            cat = l_list[0]
+            if cat in _file_to_liner_dispatch:
+                cat_name = cat
+                length = int((len(l_list) - 2) / 2)
+                gen_name = ' '.join(l_list[(1 + length):(1 + 2 * length)])
+                flx_name = ' '.join(l_list[1:(1 + length)])
+                flex = l_list[-1]
+                if cat_name not in _form_dict:
+                    _form_dict[cat_name] = dict()
+                if length not in _form_dict[cat_name]:
+                    _form_dict[cat_name][length] = dict()
+                if gen_name not in _form_dict[cat_name][length]:
+                    _form_dict[cat_name][length][gen_name] = dict()
+                if flex not in _form_dict[cat_name][length][gen_name]:
+                    _form_dict[cat_name][length][gen_name][flex] = flx_name
+                    name = gen_name.split(' ')[0]
+                    generate = morf.generate(name)
+                    flex_split = generate[0][2].split(':')
+                    if len(flex_split) > 3:
+                        gender = flex_split[3]
+                        new_flex = flex + ':' + gender
+                        output.write(cat + '\t' + flx_name + '\t' +
+                                     gen_name + '\t' + new_flex + '\n')
+
+
+def _last_names(output):
+    dict_list = list()
+    with open('nelexicon2/extra/wikipedia-liner2.txt',
+              'rt',
+              encoding='utf-8'
+              ) as f:
+        for line in f:
+            line = line.strip()
+            line_l = line.split('\t')
+            if line_l[0] == 'nam_liv_person_last':
+                line_l = line_l[1]
+                line_l.split(' ')
+                line_len = len(line_l)
+                if type(line_l) == list() and line_len > 1:
+                    dictionary = dict()
+                    for word in line_l:
+                        gen = morf.generate(word)
+                        for w in gen:
+                            tag_list = w[2].split(':')
+                            if len(tag_list) > 3:
+                                tag = tag_list[1] + ':' + tag_list[2]
+                                if tag not in dictionary:
+                                    dictionary[tag] = w[0]
+                                else:
+                                    dictionary[tag] += ' ' + w[0]
+                    for key in dictionary:
+                        if len(dictionary[key].split(' ')) == line_len:
+                            d = dictionary[key]
+                            dict_list.append(d)
+                else:
+                    word = line_l[0] if type(line_l) == list() else line_l
+                    generate = morf.generate(word)
+                    for g in generate:
+                        if len(g) > 4 and 'nazwisko' in g[3]:
+                            dict_list.append(g)
+    for word in dict_list:
+        d = word
+        line = 'nam_liv_person_last' + '\t' + d[0].split(':')[0] +\
+               '\t' + d[1].split(':')[0] + '\t' + ':'.join(d[2].split(':')[1:])
+        output.write(line + '\n')
+
+
+_create_wiki()