From 64a66811a0c4a52292e8a67d1b7c17e381643421 Mon Sep 17 00:00:00 2001
From: Grzegorz Kostkowski <grzegorz.kostkowski@pwr.edu.pl>
Date: Thu, 25 Feb 2021 18:28:22 +0100
Subject: [PATCH 1/3] Move method sentence2str, add missed methods to _all
---
cclutils/_base.py | 30 ++++++++++++++++++++++++++++++
cclutils/_copies.py | 31 +------------------------------
2 files changed, 31 insertions(+), 30 deletions(-)
diff --git a/cclutils/_base.py b/cclutils/_base.py
index 8e49df1..7dd0e7e 100644
--- a/cclutils/_base.py
+++ b/cclutils/_base.py
@@ -12,7 +12,10 @@ __all__ = [
'read',
'write',
'read_from_directory',
+ 'read_chunks_it',
+ 'read_sentences_it',
'get_tagset',
+ 'sentence2str'
]
@@ -206,3 +209,30 @@ def read_sentences_it(filepath, tagset='nkjp'):
yield sentence
del reader
+
+
+def sentence2str(sentence, use_bases=False, tagset='nkjp'):
+ """ Return corpus2.Sentence as a string.
+
+ Args:
+ sentence: a sentence object (corpus2.Sentence).
+ use_bases: if set to True, the we take base forms
+ instead of taking the orths.
+
+ Returns:
+ a string representation of the input sentence object.
+
+ """
+ if isinstance(tagset, str):
+ tagset = corpus2.get_named_tagset(tagset)
+
+ text = []
+ for token in sentence.tokens():
+ text.append(" " if token.after_space() else "")
+ if not use_bases:
+ token_string = token.orth_utf8()
+ else:
+ token_string = token.get_preferred_lexeme(tagset).lemma_utf8()
+ text.append(token_string)
+
+ return "".join(text).strip()
diff --git a/cclutils/_copies.py b/cclutils/_copies.py
index 9f033b2..ac92d92 100644
--- a/cclutils/_copies.py
+++ b/cclutils/_copies.py
@@ -9,8 +9,7 @@ ENCODING = "utf-8"
__all__ = [
'copy_chunk',
'copy_sentence',
- 'copy_relation',
- 'sentence2str'
+ 'copy_relation'
]
@@ -119,31 +118,3 @@ def _copy_chunk_attributes(source_chunk, target_chunk):
"""
for key, value in list(source_chunk.attributes().items()):
target_chunk.set_attribute(key, value)
-
-
-# todo: move somewhere else!
-def sentence2str(sentence, use_bases=False, tagset='nkjp'):
- """ Return corpus2.Sentence as a string.
-
- Args:
- sentence: a sentence object (corpus2.Sentence).
- use_bases: if set to True, the we take base forms
- instead of taking the orths.
-
- Returns:
- a string representation of the input sentence object.
-
- """
- if isinstance(tagset, str):
- tagset = corpus2.get_named_tagset(tagset)
-
- text = []
- for token in sentence.tokens():
- text.append(" " if token.after_space() else "")
- if not use_bases:
- token_string = token.orth_utf8()
- else:
- token_string = token.get_preferred_lexeme(tagset).lemma_utf8()
- text.append(token_string)
-
- return "".join(text).strip()
--
GitLab
From 7f72cc26670f917e94245bc7ed274bed2092de14 Mon Sep 17 00:00:00 2001
From: Grzegorz Kostkowski <grzegorz.kostkowski@pwr.edu.pl>
Date: Fri, 26 Feb 2021 06:22:13 +0100
Subject: [PATCH 2/3] Add gitlab CI config
---
.gitlab-ci.yml | 37 +++++++++++++++++++++++++++++++++++++
1 file changed, 37 insertions(+)
create mode 100644 .gitlab-ci.yml
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
new file mode 100644
index 0000000..174d777
--- /dev/null
+++ b/.gitlab-ci.yml
@@ -0,0 +1,37 @@
+image: clarinpl/python:3.6
+
+before_script:
+ - pip install tox==2.9.1
+
+cache:
+ paths:
+ - .tox
+
+stages:
+ - check_style
+ - push_wheel
+
+pep8:
+ stage: check_style
+ script:
+ - tox -v -e pep8
+
+docstyle:
+ stage: check_style
+ script:
+ - tox -v -e docstyle
+
+push_wheel:
+ before_script:
+ - pip install twine
+ only:
+ - master
+ stage: push_wheel
+ when: on_success
+ script:
+ - python setup.py sdist bdist_wheel
+ - python -m twine upload
+ --repository-url https://pypi.clarin-pl.eu/
+ -u $PIPY_USER -p $PIPY_PASS dist/cclutils*.whl
+
+
--
GitLab
From c1f5d0e30fec9890206ba734a146512511606763 Mon Sep 17 00:00:00 2001
From: Grzegorz Kostkowski <grzegorz.kostkowski@pwr.edu.pl>
Date: Fri, 26 Feb 2021 09:02:44 +0100
Subject: [PATCH 3/3] Add missing tox.ini
---
tox.ini | 45 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 45 insertions(+)
create mode 100644 tox.ini
diff --git a/tox.ini b/tox.ini
new file mode 100644
index 0000000..70f02ca
--- /dev/null
+++ b/tox.ini
@@ -0,0 +1,45 @@
+[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
+
--
GitLab