1
0
mirror of https://github.com/gsi-upm/senpy synced 2025-10-19 09:48:26 +00:00

Compare commits

..

1 Commits

Author SHA1 Message Date
J. Fernando Sánchez
5493070d40 Filter conversion plugins
Closes #12

* Shows only analysis plugins by default on /api/plugins
* Adds a plugin_type parameter to get other types of plugins
* default_plugin chosen from analysis plugins
2017-03-06 11:27:49 +01:00
88 changed files with 1112 additions and 3092 deletions

View File

@@ -1,19 +1,18 @@
# Uncomment if you want to use docker-in-docker
# image: gsiupm/dockermake:latest
# services:
# - docker:dind
image: gsiupm/dockermake:latest
# When using dind, it's wise to use the overlayfs driver for
# improved performance.
variables:
DOCKER_DRIVER: overlay
DOCKERFILE: Dockerfile
IMAGENAME: $CI_REGISTRY_IMAGE
stages:
- test
- push
- deploy
- clean
before_script:
- make -e login
.test: &test_definition
stage: test
script:
@@ -29,14 +28,16 @@ test-2.7:
variables:
PYTHON_VERSION: "2.7"
.image: &image_definition
stage: push
before_script:
- docker login -u gitlab-ci-token -p $CI_BUILD_TOKEN $CI_REGISTRY
script:
- make -e push-$PYTHON_VERSION
only:
- tags
- triggers
- fix-makefiles
push-3.5:
<<: *image_definition
@@ -56,55 +57,9 @@ push-latest:
- master
- triggers
push-github:
stage: deploy
script:
- make -e push-github
only:
- master
- triggers
- fix-makefiles
deploy_pypi:
stage: deploy
script: # Configure the PyPI credentials, then push the package, and cleanup the creds.
- echo "[server-login]" >> ~/.pypirc
- echo "repository=https://upload.pypi.org/legacy/" >> ~/.pypirc
- echo "username=" ${PYPI_USER} >> ~/.pypirc
- echo "password=" ${PYPI_PASSWORD} >> ~/.pypirc
- make pip_upload
- echo "" > ~/.pypirc && rm ~/.pypirc # If the above fails, this won't run.
only:
- /^v?\d+\.\d+\.\d+([abc]\d*)?$/ # PEP-440 compliant version (tags)
except:
- branches
deploy:
stage: deploy
environment: test
script:
- make -e deploy
only:
- master
- fix-makefiles
push-github:
stage: deploy
script:
- make -e push-github
only:
- master
- triggers
clean :
stage: clean
script:
- make -e clean
when: manual
cleanup_py:
stage: clean
when: always # this is important; run even if preceding stages failed.
script:
- rm -vf ~/.pypirc # we don't want to leave these around, but GitLab may clean up anyway.
- docker logout
only:
- master

View File

@@ -1,27 +0,0 @@
These makefiles are recipes for several common tasks in different types of projects.
To add them to your project, simply do:
```
git remote add makefiles ssh://git@lab.cluster.gsi.dit.upm.es:2200/docs/templates/makefiles.git
git subtree add --prefix=.makefiles/ makefiles master
touch Makefile
echo "include .makefiles/base.mk" >> Makefile
```
Now you can take advantage of the recipes.
For instance, to add useful targets for a python project, just add this to your Makefile:
```
include .makefiles/python.mk
```
You may need to set special variables like the name of your project or the python versions you're targetting.
Take a look at each specific `.mk` file for more information, and the `Makefile` in the [senpy](https://lab.cluster.gsi.dit.upm.es/senpy/senpy) project for a real use case.
If you update the makefiles from your repository, make sure to push the changes for review in upstream (this repository):
```
make makefiles-push
```
It will automatically commit all unstaged changes in the .makefiles folder.

View File

@@ -1,38 +0,0 @@
export
NAME ?= $(shell basename $(CURDIR))
VERSION ?= $(shell git describe --tags --dirty 2>/dev/null)
# Get the location of this makefile.
MK_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
-include .env
-include ../.env
.FORCE:
version: .FORCE
@echo $(VERSION) > $(NAME)/VERSION
@echo $(VERSION)
help: ## Show this help.
@fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/\(.*:\)[^#]*##\s*\(.*\)/\1\t\2/' | column -t -s " "
config: ## Load config from the environment. You should run it once in every session before other tasks. Run: eval $(make config)
@awk '{ print "export " $$0}' ../.env
@awk '{ print "export " $$0}' .env
@echo "# Please, run: "
@echo "# eval \$$(make config)"
# If you need to run a command on the key/value pairs, use this:
# @awk '{ split($$0, a, "="); "echo " a[2] " | base64 -w 0" |& getline b64; print "export " a[1] "=" a[2]; print "export " a[1] "_BASE64=" b64}' .env
ci: ## Run a task using gitlab-runner. Only use to debug problems in the CI pipeline
gitlab-runner exec shell --builds-dir '.builds' --env CI_PROJECT_NAME=$(NAME) ${action}
include $(MK_DIR)/makefiles.mk
include $(MK_DIR)/docker.mk
include $(MK_DIR)/git.mk
info:: ## List all variables
env
.PHONY:: config help ci version .FORCE

View File

@@ -1,25 +0,0 @@
IMAGEWTAG ?= $(IMAGENAME):$(VERSION)
docker-login: ## Log in to the registry. It will only be used in the server, or when running a CI task locally (if CI_BUILD_TOKEN is set).
ifeq ($(CI_BUILD_TOKEN),)
@echo "Not logging in to the docker registry" "$(CI_REGISTRY)"
else
@docker login -u gitlab-ci-token -p $(CI_BUILD_TOKEN) $(CI_REGISTRY)
endif
ifeq ($(HUB_USER),)
@echo "Not logging in to global the docker registry"
else
@docker login -u $(HUB_USER) -p $(HUB_PASSWORD)
endif
docker-clean: ## Remove docker credentials
ifeq ($(HUB_USER),)
else
@docker logout
endif
login:: docker-login
clean:: docker-clean
.PHONY:: docker-login docker-clean login clean

View File

@@ -1,28 +0,0 @@
commit:
git commit -a
tag:
git tag ${VERSION}
git-push::
git push --tags -u origin HEAD
git-pull:
git pull --all
push-github: ## Push the code to github. You need to set up GITHUB_DEPLOY_KEY
ifeq ($(GITHUB_DEPLOY_KEY),)
else
$(eval KEY_FILE := "$(shell mktemp)")
@echo "$(GITHUB_DEPLOY_KEY)" > $(KEY_FILE)
@git remote rm github-deploy || true
git remote add github-deploy $(GITHUB_REPO)
-@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git fetch github-deploy $(CI_COMMIT_REF_NAME)
@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git push github-deploy HEAD:$(CI_COMMIT_REF_NAME)
rm $(KEY_FILE)
endif
push:: git-push
pull:: git-pull
.PHONY:: commit tag push git-push git-pull push-github

View File

@@ -1,51 +0,0 @@
# Deployment with Kubernetes
# KUBE_CA_PEM_FILE is the path of a certificate file. It automatically set by GitLab
# if you enable Kubernetes integration in a project.
#
# As of this writing, Kubernetes integration can not be set on a group level, so it has to
# be manually set in every project.
# Alternatively, we use a custom KUBE_CA_BUNDLE environment variable, which can be set at
# the group level. In this case, the variable contains the whole content of the certificate,
# which we dump to a temporary file
#
# Check if the KUBE_CA_PEM_FILE exists. Otherwise, create it from KUBE_CA_BUNDLE
KUBE_CA_TEMP=false
ifndef KUBE_CA_PEM_FILE
KUBE_CA_PEM_FILE:=$$PWD/.ca.crt
CREATED:=$(shell echo -e "$(KUBE_CA_BUNDLE)" > $(KUBE_CA_PEM_FILE))
endif
KUBE_TOKEN?=""
KUBE_NAMESPACE?=$(NAME)
KUBECTL=docker run --rm -v $(KUBE_CA_PEM_FILE):/tmp/ca.pem -i lachlanevenson/k8s-kubectl --server="$(KUBE_URL)" --token="$(KUBE_TOKEN)" --certificate-authority="/tmp/ca.pem" -n $(KUBE_NAMESPACE)
CI_COMMIT_REF_NAME?=master
info:: ## Print variables. Useful for debugging.
@echo "#KUBERNETES"
@echo KUBE_URL=$(KUBE_URL)
@echo KUBE_CA_PEM_FILE=$(KUBE_CA_PEM_FILE)
@echo KUBE_CA_BUNDLE=$$KUBE_CA_BUNDLE
@echo KUBE_TOKEN=$(KUBE_TOKEN)
@echo KUBE_NAMESPACE=$(KUBE_NAMESPACE)
@echo KUBECTL=$(KUBECTL)
@echo "#CI"
@echo CI_PROJECT_NAME=$(CI_PROJECT_NAME)
@echo CI_REGISTRY=$(CI_REGISTRY)
@echo CI_REGISTRY_USER=$(CI_REGISTRY_USER)
@echo CI_COMMIT_REF_NAME=$(CI_COMMIT_REF_NAME)
@echo "CREATED=$(CREATED)"
#
# Deployment and advanced features
#
deploy: ## Deploy to kubernetes using the credentials in KUBE_CA_PEM_FILE (or KUBE_CA_BUNDLE ) and TOKEN
@ls k8s/*.yaml k8s/*.yml k8s/*.tmpl 2>/dev/null || true
@cat k8s/*.yaml k8s/*.yml k8s/*.tmpl 2>/dev/null | envsubst | $(KUBECTL) apply -f -
deploy-check: ## Get the deployed configuration.
@$(KUBECTL) get deploy,pods,svc,ingress
.PHONY:: info deploy deploy-check

View File

@@ -1,17 +0,0 @@
makefiles-remote:
@git remote add makefiles ssh://git@lab.cluster.gsi.dit.upm.es:2200/docs/templates/makefiles.git 2>/dev/null || true
makefiles-commit: makefiles-remote
git add -f .makefiles
git commit -em "Updated makefiles from ${NAME}"
makefiles-push:
git subtree push --prefix=.makefiles/ makefiles $(NAME)
makefiles-pull: makefiles-remote
git subtree pull --prefix=.makefiles/ makefiles master --squash
pull:: makefiles-pull
push:: makefiles-push
.PHONY:: makefiles-remote makefiles-commit makefiles-push makefiles-pull pull push

View File

@@ -1,5 +0,0 @@
init: ## Init pre-commit hooks (i.e. enforcing format checking before allowing a commit)
pip install --user pre-commit
pre-commit install
.PHONY:: init

View File

@@ -1,92 +0,0 @@
PYVERSIONS ?= 2.7
PYMAIN ?= $(firstword $(PYVERSIONS))
TARNAME ?= $(NAME)-$(VERSION).tar.gz
DEVPORT ?= 6000
yapf: ## Format python code
yapf -i -r $(NAME)
yapf -i -r tests
dockerfiles: $(addprefix Dockerfile-,$(PYVERSIONS)) ## Generate dockerfiles for each python version
@unlink Dockerfile >/dev/null
ln -s Dockerfile-$(PYMAIN) Dockerfile
Dockerfile-%: Dockerfile.template ## Generate a specific dockerfile (e.g. Dockerfile-2.7)
sed "s/{{PYVERSION}}/$*/" Dockerfile.template > Dockerfile-$*
quick_build: $(addprefix build-, $(PYMAIN))
build: $(addprefix build-, $(PYVERSIONS)) ## Build all images / python versions
build-%: version Dockerfile-% ## Build a specific version (e.g. build-2.7)
docker build -t '$(IMAGEWTAG)-python$*' --cache-from $(IMAGENAME):python$* -f Dockerfile-$* .;
dev-%: ## Launch a specific development environment using docker (e.g. dev-2.7)
@docker start $(NAME)-dev$* || (\
$(MAKE) build-$*; \
docker run -d -w /usr/src/app/ -p $(DEVPORT):5000 -v $$PWD:/usr/src/app --entrypoint=/bin/bash -ti --name $(NAME)-dev$* '$(IMAGEWTAG)-python$*'; \
)\
docker exec -ti $(NAME)-dev$* bash
dev: dev-$(PYMAIN) ## Launch a development environment using docker, using the default python version
quick_test: test-$(PYMAIN)
test-%: ## Run setup.py from in an isolated container, built from the base image. (e.g. test-2.7)
# This speeds tests up because the image has most (if not all) of the dependencies already.
docker rm $(NAME)-test-$* || true
docker create -ti --name $(NAME)-test-$* --entrypoint="" -w /usr/src/app/ $(IMAGENAME):python$* python setup.py test
docker cp . $(NAME)-test-$*:/usr/src/app
docker start -a $(NAME)-test-$*
test: $(addprefix test-,$(PYVERSIONS)) ## Run the tests with the main python version
run-%: build-%
docker run --rm -p $(DEVPORT):5000 -ti '$(IMAGEWTAG)-python$(PYMAIN)' --default-plugins
run: run-$(PYMAIN)
# Pypy - Upload a package
dist/$(TARNAME): version
python setup.py sdist;
sdist: dist/$(TARNAME) ## Generate the distribution file (wheel)
pip_test-%: sdist ## Test the distribution file using pip install and a specific python version (e.g. pip_test-2.7)
docker run --rm -v $$PWD/dist:/dist/ python:$* pip install /dist/$(TARNAME);
pip_test: $(addprefix pip_test-,$(PYVERSIONS)) ## Test pip installation with the main python version
pip_upload: pip_test ## Upload package to pip
python setup.py sdist upload ;
# Pushing to docker
push-latest: $(addprefix push-latest-,$(PYVERSIONS)) ## Push the "latest" tag to dockerhub
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGENAME)'
docker push '$(IMAGENAME):latest'
docker push '$(IMAGEWTAG)'
push-latest-%: build-% ## Push the latest image for a specific python version
docker tag $(IMAGENAME):$(VERSION)-python$* $(IMAGENAME):python$*
docker push $(IMAGENAME):$(VERSION)-python$*
docker push $(IMAGENAME):python$*
push-%: build-% ## Push the image of the current version (tagged). e.g. push-2.7
docker push $(IMAGENAME):$(VERSION)-python$*
push:: $(addprefix push-,$(PYVERSIONS)) ## Push an image with the current version for every python version
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker push $(IMAGENAME):$(VERSION)
clean:: ## Clean older docker images and containers related to this project and dev environments
@docker stop $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
@docker rm $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
@docker ps -a | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1;}}' | xargs docker rm -v 2>/dev/null|| true
@docker images | grep $(IMAGENAME) | awk '{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1":"$$2;}}' | xargs docker rmi 2>/dev/null|| true
.PHONY:: yapf dockerfiles Dockerfile-% quick_build build build-% dev-% quick-dev test quick_test push-latest push-latest-% push-% push

View File

@@ -7,6 +7,7 @@ language: python
env:
- PYV=2.7
- PYV=3.4
- PYV=3.5
# run nosetests - Tests
script: make test-$PYV

View File

@@ -17,6 +17,6 @@ WORKDIR /usr/src/app
COPY test-requirements.txt requirements.txt /usr/src/app/
RUN pip install --use-wheel -r test-requirements.txt -r requirements.txt
COPY . /usr/src/app/
RUN pip install --no-index --no-deps --editable .
RUN pip install --no-deps --no-index .
ENTRYPOINT ["python", "-m", "senpy", "-f", "/senpy-plugins/", "--host", "0.0.0.0"]

120
Makefile
View File

@@ -1,17 +1,109 @@
NAME=senpy
GITHUB_REPO=git@github.com:gsi-upm/senpy.git
IMAGENAME=gsiupm/senpy
# The first version is the main one (used for quick builds)
# See .makefiles/python.mk for more info
PYVERSIONS=3.5 2.7
DEVPORT=5000
PYMAIN=$(firstword $(PYVERSIONS))
NAME=senpy
REPO=gsiupm
VERSION=$(shell git describe --tags --dirty 2>/dev/null)
TARNAME=$(NAME)-$(VERSION).tar.gz
IMAGENAME=$(REPO)/$(NAME)
IMAGEWTAG=$(IMAGENAME):$(VERSION)
action="test-${PYMAIN}"
GITHUB_REPO=git@github.com:gsi-upm/senpy.git
include .makefiles/base.mk
include .makefiles/k8s.mk
include .makefiles/python.mk
all: build run
.FORCE:
version: .FORCE
@echo $(VERSION) > $(NAME)/VERSION
@echo $(VERSION)
yapf:
yapf -i -r senpy
yapf -i -r tests
init:
pip install --user pre-commit
pre-commit install
dockerfiles: $(addprefix Dockerfile-,$(PYVERSIONS))
@unlink Dockerfile >/dev/null
ln -s Dockerfile-$(PYMAIN) Dockerfile
Dockerfile-%: Dockerfile.template
sed "s/{{PYVERSION}}/$*/" Dockerfile.template > Dockerfile-$*
quick_build: $(addprefix build-, $(PYMAIN))
build: $(addprefix build-, $(PYVERSIONS))
build-%: version Dockerfile-%
docker build -t '$(IMAGEWTAG)-python$*' -f Dockerfile-$* .;
quick_test: $(addprefix test-,$(PYMAIN))
dev-%:
@docker start $(NAME)-dev$* || (\
$(MAKE) build-$*; \
docker run -d -w /usr/src/app/ -v $$PWD:/usr/src/app --entrypoint=/bin/bash -ti --name $(NAME)-dev$* '$(IMAGEWTAG)-python$*'; \
)\
docker exec -ti $(NAME)-dev$* bash
dev: dev-$(PYMAIN)
test-all: $(addprefix test-,$(PYVERSIONS))
test-%: build-%
docker run --rm --entrypoint /usr/local/bin/python -w /usr/src/app $(IMAGEWTAG)-python$* setup.py test
test: test-$(PYMAIN)
dist/$(TARNAME):
docker run --rm -ti -v $$PWD:/usr/src/app/ -w /usr/src/app/ python:$(PYMAIN) python setup.py sdist;
sdist: dist/$(TARNAME)
pip_test-%: sdist
docker run --rm -v $$PWD/dist:/dist/ -ti python:$* pip install /dist/$(TARNAME);
pip_test: $(addprefix pip_test-,$(PYVERSIONS))
clean:
@docker ps -a | awk '/$(REPO)\/$(NAME)/{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1;}}' | xargs docker rm -v 2>/dev/null|| true
@docker images | awk '/$(REPO)\/$(NAME)/{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1":"$$2;}}' | xargs docker rmi 2>/dev/null|| true
@docker rmi $(NAME)-dev 2>/dev/null || true
git_commit:
git commit -a
git_tag:
git tag ${VERSION}
git_push:
git push --tags origin master
pip_upload:
python setup.py sdist upload ;
run-%: build-%
docker run --rm -p 5000:5000 -ti '$(IMAGEWTAG)-python$(PYMAIN)' --default-plugins
run: run-$(PYMAIN)
push-latest: build-$(PYMAIN)
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGENAME)'
docker push '$(IMAGENAME):latest'
docker push '$(IMAGEWTAG)'
push-%: build-%
docker push $(IMAGENAME):$(VERSION)-python$*
push: $(addprefix push-,$(PYVERSIONS))
docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
docker push $(IMAGENAME):$(VERSION)
ci:
gitlab-runner exec docker --docker-volumes /var/run/docker.sock:/var/run/docker.sock --env CI_PROJECT_NAME=$(NAME) ${action}
.PHONY: test test-% test-all build-% build test pip_test run yapf push-main push-% dev ci version .FORCE

View File

@@ -23,7 +23,7 @@ Through PIP
.. code:: bash
pip install -U --user senpy
pip install --user senpy
Alternatively, you can use the development version:
@@ -42,53 +42,6 @@ Build the image or use the pre-built one: ``docker run -ti -p 5000:5000 gsiupm/s
To add custom plugins, add a volume and tell senpy where to find the plugins: ``docker run -ti -p 5000:5000 -v <PATH OF PLUGINS>:/plugins gsiupm/senpy --default-plugins -f /plugins``
Developing
----------
Developing/debugging
********************
This command will run the senpy container using the latest image available, mounting your current folder so you get your latest code:
.. code:: bash
# Python 3.5
make dev
# Python 2.7
make dev-2.7
Building a docker image
***********************
.. code:: bash
# Python 3.5
make build-3.5
# Python 2.7
make build-2.7
Testing
*******
.. code:: bash
make test
Running
*******
This command will run the senpy server listening on localhost:5000
.. code:: bash
# Python 3.5
make run-3.5
# Python 2.7
make run-2.7
Usage
-----
@@ -96,14 +49,12 @@ However, the easiest and recommended way is to just use the command-line tool to
.. code:: bash
senpy
or, alternatively:
.. code:: bash
python -m senpy

View File

@@ -1,317 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:05:31.465571Z",
"start_time": "2017-04-10T19:05:31.458282+02:00"
},
"deletable": true,
"editable": true
},
"source": [
"# Client"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true,
"deletable": true,
"editable": true
},
"source": [
"The built-in senpy client allows you to query any Senpy endpoint. We will illustrate how to use it with the public demo endpoint, and then show you how to spin up your own endpoint using docker."
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"Demo Endpoint\n",
"-------------"
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"To start using senpy, simply create a new Client and point it to your endpoint. In this case, the latest version of Senpy at GSI."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:29:12.827640Z",
"start_time": "2017-04-10T19:29:12.818617+02:00"
},
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"from senpy.client import Client\n",
"\n",
"c = Client('http://latest.senpy.cluster.gsi.dit.upm.es/api')\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"Now, let's use that client analyse some queries:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:29:14.011657Z",
"start_time": "2017-04-10T19:29:13.701808+02:00"
},
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"r = c.analyse('I like sugar!!', algorithm='sentiment140')\n",
"r"
]
},
{
"cell_type": "markdown",
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:08:19.616754Z",
"start_time": "2017-04-10T19:08:19.610767+02:00"
},
"deletable": true,
"editable": true
},
"source": [
"As you can see, that gave us the full JSON result. A more concise way to print it would be:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:29:14.854213Z",
"start_time": "2017-04-10T19:29:14.842068+02:00"
},
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"for entry in r.entries:\n",
" print('{} -> {}'.format(entry['text'], entry['sentiments'][0]['marl:hasPolarity']))"
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"We can also obtain a list of available plugins with the client:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:29:16.245198Z",
"start_time": "2017-04-10T19:29:16.056545+02:00"
},
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"c.plugins()"
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"Or, more concisely:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:29:17.663275Z",
"start_time": "2017-04-10T19:29:17.484623+02:00"
},
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"c.plugins().keys()"
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"Local Endpoint\n",
"--------------"
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"To run your own instance of senpy, just create a docker container with the latest Senpy image. Using `--default-plugins` you will get some extra plugins to start playing with the API."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:29:20.637539Z",
"start_time": "2017-04-10T19:29:19.938322+02:00"
},
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"!docker run -ti --name 'SenpyEndpoint' -d -p 6000:5000 gsiupm/senpy:0.8.6 --host 0.0.0.0 --default-plugins"
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"To use this endpoint:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:29:21.263976Z",
"start_time": "2017-04-10T19:29:21.260595+02:00"
},
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"c_local = Client('http://127.0.0.1:6000/api')"
]
},
{
"cell_type": "markdown",
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"That's all! After you are done with your analysis, stop the docker container:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2017-04-10T17:29:33.226686Z",
"start_time": "2017-04-10T19:29:22.392121+02:00"
},
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
"!docker stop SenpyEndpoint\n",
"!docker rm SenpyEndpoint"
]
}
],
"metadata": {
"anaconda-cloud": {},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.0"
},
"toc": {
"colors": {
"hover_highlight": "#DAA520",
"running_highlight": "#FF0000",
"selected_highlight": "#FFD700"
},
"moveMenuLeft": true,
"nav_menu": {
"height": "68px",
"width": "252px"
},
"navigate_menu": true,
"number_sections": true,
"sideBar": true,
"threshold": 4,
"toc_cell": false,
"toc_section_display": "block",
"toc_window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 1
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 208 KiB

View File

@@ -1,11 +0,0 @@
About
--------
If you use Senpy in your research, please cite `Senpy: A Pragmatic Linked Sentiment Analysis Framework <http://gsi.dit.upm.es/index.php/es/investigacion/publicaciones?view=publication&task=show&id=417>`__ (`BibTex <http://gsi.dit.upm.es/index.php/es/investigacion/publicaciones?controller=publications&task=export&format=bibtex&id=417>`__):
.. code-block:: text
Sánchez-Rada, J. F., Iglesias, C. A., Corcuera, I., & Araque, Ó. (2016, October).
Senpy: A Pragmatic Linked Sentiment Analysis Framework.
In Data Science and Advanced Analytics (DSAA),
2016 IEEE International Conference on (pp. 735-742). IEEE.

View File

@@ -1,5 +1,5 @@
NIF API
-------
=======
.. http:get:: /api
Basic endpoint for sentiment/emotion analysis.
@@ -22,32 +22,38 @@ NIF API
Content-Type: text/javascript
{
"@context":"http://127.0.0.1/api/contexts/Results.jsonld",
"@id":"_:Results_11241245.22",
"@type":"results"
"analysis": [
"plugins/sentiment-140_0.1"
],
"entries": [
{
"@id": "_:Entry_11241245.22"
"@type":"entry",
"emotions": [],
"entities": [],
"sentiments": [
{
"@id": "Sentiment0",
"@type": "sentiment",
"marl:hasPolarity": "marl:Negative",
"marl:polarityValue": 0,
"prefix": ""
}
],
"suggestions": [],
"text": "This text makes me sad.\nwhilst this text makes me happy and surprised at the same time.\nI cannot believe it!",
"topics": []
}
]
"@context": [
"http://127.0.0.1/static/context.jsonld",
],
"analysis": [
{
"@id": "SentimentAnalysisExample",
"@type": "marl:SentimentAnalysis",
"dc:language": "en",
"marl:maxPolarityValue": 10.0,
"marl:minPolarityValue": 0.0
}
],
"domain": "wndomains:electronics",
"entries": [
{
"opinions": [
{
"prov:generatedBy": "SentimentAnalysisExample",
"marl:polarityValue": 7.8,
"marl:hasPolarity": "marl:Positive",
"marl:describesObject": "http://www.gsi.dit.upm.es",
}
],
"nif:isString": "I love GSI",
"strings": [
{
"nif:anchorOf": "GSI",
"nif:taIdentRef": "http://www.gsi.dit.upm.es"
}
]
}
]
}
:query i input: No default. Depends on informat and intype
@@ -86,59 +92,58 @@ NIF API
.. sourcecode:: http
{
"@id": "plugins/sentiment-140_0.1",
"@type": "sentimentPlugin",
"author": "@balkian",
"description": "Sentiment classifier using rule-based classification for English and Spanish. This plugin uses sentiment140 data to perform classification. For more information: http://help.sentiment140.com/for-students/",
"extra_params": {
"language": {
"@id": "lang_sentiment140",
"aliases": [
"language",
"l"
],
"options": [
"es",
"en",
"auto"
],
"required": false
}
},
"is_activated": true,
"maxPolarityValue": 1.0,
"minPolarityValue": 0.0,
"module": "sentiment-140",
"name": "sentiment-140",
"requirements": {},
"version": "0.1"
},
{
"@id": "plugins/ExamplePlugin_0.1",
"@type": "sentimentPlugin",
"author": "@balkian",
"custom_attribute": "42",
"description": "I am just an example",
"extra_params": {
"parameter": {
"@id": "parameter",
"aliases": [
"parameter",
"param"
],
"default": 42,
"required": true
}
},
"is_activated": true,
"maxPolarityValue": 1.0,
"minPolarityValue": 0.0,
"module": "example",
"name": "ExamplePlugin",
"requirements": "noop",
"version": "0.1"
}
{
"@context": {
...
},
"@type": "plugins",
"plugins": [
{
"name": "sentiment140",
"is_activated": true,
"version": "0.1",
"extra_params": {
"@id": "extra_params_sentiment140_0.1",
"language": {
"required": false,
"@id": "lang_sentiment140",
"options": [
"es",
"en",
"auto"
],
"aliases": [
"language",
"l"
]
}
},
"@id": "sentiment140_0.1"
}, {
"name": "rand",
"is_activated": true,
"version": "0.1",
"extra_params": {
"@id": "extra_params_rand_0.1",
"language": {
"required": false,
"@id": "lang_rand",
"options": [
"es",
"en",
"auto"
],
"aliases": [
"language",
"l"
]
}
},
"@id": "rand_0.1"
}
]
}
.. http:get:: /api/plugins/<pluginname>
@@ -157,60 +162,30 @@ NIF API
.. sourcecode:: http
{
"@context": "http://127.0.0.1/api/contexts/ExamplePlugin.jsonld",
"@id": "plugins/ExamplePlugin_0.1",
"@type": "sentimentPlugin",
"author": "@balkian",
"custom_attribute": "42",
"description": "I am just an example",
"extra_params": {
"parameter": {
"@id": "parameter",
"aliases": [
"parameter",
"param"
],
"default": 42,
"required": true
}
},
"is_activated": true,
"maxPolarityValue": 1.0,
"minPolarityValue": 0.0,
"module": "example",
"name": "ExamplePlugin",
"requirements": "noop",
"version": "0.1"
"@id": "rand_0.1",
"@type": "sentimentPlugin",
"extra_params": {
"@id": "extra_params_rand_0.1",
"language": {
"@id": "lang_rand",
"aliases": [
"language",
"l"
],
"options": [
"es",
"en",
"auto"
],
"required": false
}
},
"is_activated": true,
"name": "rand",
"version": "0.1"
}
.. http:get:: /api/plugins/default
Return the information about the default plugin.

View File

@@ -1,7 +0,0 @@
API and Examples
################
.. toctree::
vocabularies.rst
api.rst
examples.rst

View File

@@ -1,4 +1,4 @@
{
"@type": "plugins",
"plugins": {}
"plugins": [
]
}

View File

@@ -1,77 +0,0 @@
{
"@context": "http://mixedemotions-project.eu/ns/context.jsonld",
"@id": "me:Result1",
"@type": "results",
"analysis": [
"me:SAnalysis1",
"me:SgAnalysis1",
"me:EmotionAnalysis1",
"me:NER1",
{
"description": "missing @id and @type"
}
],
"entries": [
{
"@id": "http://micro.blog/status1",
"@type": [
"nif:RFC5147String",
"nif:Context"
],
"nif:isString": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"entities": [
{
"@id": "http://micro.blog/status1#char=5,13",
"nif:beginIndex": 5,
"nif:endIndex": 13,
"nif:anchorOf": "Microsoft",
"me:references": "http://dbpedia.org/page/Microsoft",
"prov:wasGeneratedBy": "me:NER1"
},
{
"@id": "http://micro.blog/status1#char=25,37",
"nif:beginIndex": 25,
"nif:endIndex": 37,
"nif:anchorOf": "Windows Phone",
"me:references": "http://dbpedia.org/page/Windows_Phone",
"prov:wasGeneratedBy": "me:NER1"
}
],
"suggestions": [
{
"@id": "http://micro.blog/status1#char=16,77",
"nif:beginIndex": 16,
"nif:endIndex": 77,
"nif:anchorOf": "put your Windows Phone on your newest #open technology program",
"prov:wasGeneratedBy": "me:SgAnalysis1"
}
],
"sentiments": [
{
"@id": "http://micro.blog/status1#char=80,97",
"nif:beginIndex": 80,
"nif:endIndex": 97,
"nif:anchorOf": "You'll be awesome.",
"marl:hasPolarity": "marl:Positive",
"marl:polarityValue": 0.9,
"prov:wasGeneratedBy": "me:SAnalysis1"
}
],
"emotions": [
{
"@id": "http://micro.blog/status1#char=0,109",
"nif:anchorOf": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"prov:wasGeneratedBy": "me:EAnalysis1",
"onyx:hasEmotion": [
{
"onyx:hasEmotionCategory": "wna:liking"
},
{
"onyx:hasEmotionCategory": "wna:excitement"
}
]
}
]
}
]
}

View File

@@ -1,9 +0,0 @@
Command line
============
This video shows how to analyse text directly on the command line using the senpy tool.
.. image:: https://asciinema.org/a/9uwef1ghkjk062cw2t4mhzpyk.png
:width: 100%
:target: https://asciinema.org/a/9uwef1ghkjk062cw2t4mhzpyk
:alt: CLI demo

View File

@@ -37,7 +37,6 @@ extensions = [
'sphinx.ext.todo',
'sphinxcontrib.httpdomain',
'sphinx.ext.coverage',
'sphinx.ext.autosectionlabel',
]
# Add any paths that contain templates here, relative to this directory.
@@ -55,21 +54,20 @@ master_doc = 'index'
# General information about the project.
project = u'Senpy'
copyright = u'2016, J. Fernando Sánchez'
description = u'A framework for sentiment and emotion analysis services'
# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
# built documents.
#
# The short X.Y version.
# with open('../senpy/VERSION') as f:
# version = f.read().strip()
with open('../senpy/VERSION') as f:
version = f.read().strip()
# The full version, including alpha/beta/rc tags.
# release = version
release = version
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
language = None
#language = None
# There are two options for replacing |today|: either, you set today to some
# non-false value, then it is used:
@@ -106,14 +104,14 @@ pygments_style = 'sphinx'
#keep_warnings = False
html_theme = 'alabaster'
# -- Options for HTML output ----------------------------------------------
# if not on_rtd: # only import and set the theme if we're building docs locally
# import sphinx_rtd_theme
# html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
if not on_rtd: # only import and set the theme if we're building docs locally
import sphinx_rtd_theme
html_theme = 'sphinx_rtd_theme'
html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
# else:
# html_theme = 'default'
else:
html_theme = 'default'
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
@@ -121,13 +119,7 @@ html_theme = 'alabaster'
# Theme options are theme-specific and customize the look and feel of a theme
# further. For a list of options available for each theme, see the
# documentation.
html_theme_options = {
'logo': 'header.png',
'github_user': 'gsi-upm',
'github_repo': 'senpy',
'github_banner': True,
}
#html_theme_options = {}
# Add any paths that contain custom themes here, relative to this directory.
#html_theme_path = []
@@ -167,13 +159,7 @@ html_static_path = ['_static']
#html_use_smartypants = True
# Custom sidebar templates, maps document names to template names.
html_sidebars = {
'**': [
'about.html',
'navigation.html',
'searchbox.html',
]
}
#html_sidebars = {}
# Additional templates that should be rendered to pages, maps page names to
# template names.

View File

@@ -1,8 +1,7 @@
Demo
----
There is a demo available on http://senpy.cluster.gsi.dit.upm.es/, where you can test a serie of different plugins.
You can use the playground (a web interface) or make HTTP requests to the service API.
There is a demo available on http://senpy.demos.gsi.dit.upm.es/, where you can a serie of different plugins. You can use them in the playground or make a directly requests to the service.
.. image:: senpy-playground.png
:height: 400px
@@ -13,4 +12,64 @@ You can use the playground (a web interface) or make HTTP requests to the servic
Plugins Demo
============
The source code and description of the plugins used in the demo is available here: https://lab.cluster.gsi.dit.upm.es/senpy/senpy-plugins-community/.
The next plugins are available at the demo:
* emoTextAnew extracts the VAD (valence-arousal-dominance) of a sentence by matching words from the ANEW dictionary.
* emoTextWordnetAffect based on the hierarchy of WordnetAffect to calculate the emotion of the sentence.
* vaderSentiment utilizes the software from vaderSentiment to calculate the sentiment of a sentence.
* sentiText is a software developed during the TASS 2015 competition, it has been adapted for English and Spanish.
emoTextANEW plugin
******************
This plugin is going to used the ANEW lexicon dictionary to calculate de VAD (valence-arousal-dominance) of the sentence and the determinate which emotion is closer to this value.
Each emotion has a centroid, which it has been approximated using the formula described in this article:
http://www.aclweb.org/anthology/W10-0208
The plugin is going to look for the words in the sentence that appear in the ANEW dictionary and calculate the average VAD score for the sentence. Once this score is calculated, it is going to seek the emotion that is closest to this value.
emoTextWAF plugin
*****************
This plugin uses WordNet-Affect (http://wndomains.fbk.eu/wnaffect.html) to calculate the percentage of each emotion. The emotions that are going to be used are: anger, fear, disgust, joy and sadness. It is has been used a emotion mapping enlarge the emotions:
* anger : general-dislike
* fear : negative-fear
* disgust : shame
* joy : gratitude, affective, enthusiasm, love, joy, liking
* sadness : ingrattitude, daze, humlity, compassion, despair, anxiety, sadness
sentiText plugin
****************
This plugin is based in the classifier developed for the TASS 2015 competition. It has been developed for Spanish and English. The different phases that has this plugin when it is activated:
* Train both classifiers (English and Spanish).
* Initialize resources (dictionaries,stopwords,etc.).
* Extract bag of words,lemmas and chars.
Once the plugin is activated, the features that are going to be extracted for the classifiers are:
* Matches with the bag of words extracted from the train corpus.
* Sentiment score of the sentences extracted from the dictionaries (lexicons and emoticons).
* Identify negations and intensifiers in the sentences.
* Complementary features such as exclamation and interrogation marks, eloganted and caps words, hashtags, etc.
The plugin has a preprocessor, which is focues on Twitter corpora, that is going to be used for cleaning the text to simplify the feature extraction.
There is more information avaliable in the next article.
Aspect based Sentiment Analysis of Spanish Tweets, Oscar Araque and Ignacio Corcuera-Platas and Constantino Román-Gómez and Carlos A. Iglesias and J. Fernando Sánchez-Rada. http://gsi.dit.upm.es/es/investigacion/publicaciones?view=publication&task=show&id=37
vaderSentiment plugin
*********************
For developing this plugin, it has been used the module vaderSentiment, which is described in the paper: VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text C.J. Hutto and Eric Gilbert Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014.
If you use this plugin in your research, please cite the above paper
For more information about the functionality, check the official repository
https://github.com/cjhutto/vaderSentiment

View File

@@ -1,78 +0,0 @@
Examples
------
All the examples in this page use the :download:`the main schema <_static/schemas/definitions.json>`.
Simple NIF annotation
.....................
Description
,,,,,,,,,,,
This example covers the basic example in the NIF documentation: `<http://persistence.uni-leipzig.org/nlp2rdf/ontologies/nif-core/nif-core.html>`_.
Representation
,,,,,,,,,,,,,,
.. literalinclude:: examples/results/example-basic.json
:language: json-ld
Sentiment Analysis
.....................
Description
,,,,,,,,,,,
This annotation corresponds to the sentiment analysis of an input. The example shows the sentiment represented according to Marl format.
The sentiments detected are contained in the Sentiments array with their related part of the text.
Representation
,,,,,,,,,,,,,,
.. literalinclude:: examples/results/example-sentiment.json
:emphasize-lines: 5-10,25-33
:language: json-ld
Suggestion Mining
.................
Description
,,,,,,,,,,,
The suggestions schema represented below shows the suggestions detected in the text. Within it, we can find the NIF fields highlighted that corresponds to the text of the detected suggestion.
Representation
,,,,,,,,,,,,,,
.. literalinclude:: examples/results/example-suggestion.json
:emphasize-lines: 5-8,22-27
:language: json-ld
Emotion Analysis
................
Description
,,,,,,,,,,,
This annotation represents the emotion analysis of an input to Senpy. The emotions are contained in the emotions section with the text that refers to following Onyx format and the emotion model defined beforehand.
Representation
,,,,,,,,,,,,,,
.. literalinclude:: examples/results/example-emotion.json
:language: json-ld
:emphasize-lines: 5-8,25-37
Named Entity Recognition
........................
Description
,,,,,,,,,,,
The Named Entity Recognition is represented as follows. In this particular case, it can be seen within the entities array the entities recognised. For the example input, Microsoft and Windows Phone are the ones detected.
Representation
,,,,,,,,,,,,,,
.. literalinclude:: examples/results/example-ner.json
:emphasize-lines: 5-8,19-34
:language: json-ld
Complete example
................
Description
,,,,,,,,,,,
This example covers all of the above cases, integrating all the annotations in the same document.
Representation
,,,,,,,,,,,,,,
.. literalinclude:: examples/results/example-complete.json
:language: json-ld

View File

@@ -1,74 +0,0 @@
{
"@context": "http://mixedemotions-project.eu/ns/context.jsonld",
"@id": "me:Result1",
"@type": "results",
"analysis": [
"me:SAnalysis1",
"me:SgAnalysis1",
"me:EmotionAnalysis1",
"me:NER1"
],
"entries": [
{
"@id": "http://micro.blog/status1",
"@type": [
"nif:RFC5147String",
"nif:Context"
],
"nif:isString": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"entities": [
{
"@id": "http://micro.blog/status1#char=5,13",
"nif:beginIndex": 5,
"nif:endIndex": 13,
"nif:anchorOf": "Microsoft",
"me:references": "http://dbpedia.org/page/Microsoft",
"prov:wasGeneratedBy": "me:NER1"
},
{
"@id": "http://micro.blog/status1#char=25,37",
"nif:beginIndex": 25,
"nif:endIndex": 37,
"nif:anchorOf": "Windows Phone",
"me:references": "http://dbpedia.org/page/Windows_Phone",
"prov:wasGeneratedBy": "me:NER1"
}
],
"suggestions": [
{
"@id": "http://micro.blog/status1#char=16,77",
"nif:beginIndex": 16,
"nif:endIndex": 77,
"nif:anchorOf": "put your Windows Phone on your newest #open technology program",
"prov:wasGeneratedBy": "me:SgAnalysis1"
}
],
"sentiments": [
{
"@id": "http://micro.blog/status1#char=80,97",
"nif:beginIndex": 80,
"nif:endIndex": 97,
"nif:anchorOf": "You'll be awesome.",
"marl:hasPolarity": "marl:Positive",
"marl:polarityValue": 0.9,
"prov:wasGeneratedBy": "me:SAnalysis1"
}
],
"emotions": [
{
"@id": "http://micro.blog/status1#char=0,109",
"nif:anchorOf": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"prov:wasGeneratedBy": "me:EAnalysis1",
"onyx:hasEmotion": [
{
"onyx:hasEmotionCategory": "wna:liking"
},
{
"onyx:hasEmotionCategory": "wna:excitement"
}
]
}
]
}
]
}

View File

@@ -1,78 +0,0 @@
{
"@context": "http://mixedemotions-project.eu/ns/context.jsonld",
"@id": "me:Result1",
"@type": "results",
"analysis": [
"me:SAnalysis1",
"me:SgAnalysis1",
"me:EmotionAnalysis1",
"me:NER1",
{
"@type": "analysis",
"@id": "anonymous"
}
],
"entries": [
{
"@id": "http://micro.blog/status1",
"@type": [
"nif:RFC5147String",
"nif:Context"
],
"nif:isString": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"entities": [
{
"@id": "http://micro.blog/status1#char=5,13",
"nif:beginIndex": 5,
"nif:endIndex": 13,
"nif:anchorOf": "Microsoft",
"me:references": "http://dbpedia.org/page/Microsoft",
"prov:wasGeneratedBy": "me:NER1"
},
{
"@id": "http://micro.blog/status1#char=25,37",
"nif:beginIndex": 25,
"nif:endIndex": 37,
"nif:anchorOf": "Windows Phone",
"me:references": "http://dbpedia.org/page/Windows_Phone",
"prov:wasGeneratedBy": "me:NER1"
}
],
"suggestions": [
{
"@id": "http://micro.blog/status1#char=16,77",
"nif:beginIndex": 16,
"nif:endIndex": 77,
"nif:anchorOf": "put your Windows Phone on your newest #open technology program",
"prov:wasGeneratedBy": "me:SgAnalysis1"
}
],
"sentiments": [
{
"@id": "http://micro.blog/status1#char=80,97",
"nif:beginIndex": 80,
"nif:endIndex": 97,
"nif:anchorOf": "You'll be awesome.",
"marl:hasPolarity": "marl:Positive",
"marl:polarityValue": 0.9,
"prov:wasGeneratedBy": "me:SAnalysis1"
}
],
"emotions": [
{
"@id": "http://micro.blog/status1#char=0,109",
"nif:anchorOf": "Dear Microsoft, put your Windows Phone on your newest #open technology program. You'll be awesome. #opensource",
"prov:wasGeneratedBy": "me:EAnalysis1",
"onyx:hasEmotion": [
{
"onyx:hasEmotionCategory": "wna:liking"
},
{
"onyx:hasEmotionCategory": "wna:excitement"
}
]
}
]
}
]
}

View File

@@ -3,7 +3,10 @@
"@id": "me:Result1",
"@type": "results",
"analysis": [
"me:SgAnalysis1"
{
"@id": "me:SgAnalysis1",
"@type": "me:SuggestionAnalysis"
}
],
"entries": [
{

View File

@@ -1,35 +1,15 @@
Welcome to Senpy's documentation!
=================================
.. image:: https://readthedocs.org/projects/senpy/badge/?version=latest
:target: http://senpy.readthedocs.io/en/latest/
.. image:: https://badge.fury.io/py/senpy.svg
:target: https://badge.fury.io/py/senpy
.. image:: https://lab.cluster.gsi.dit.upm.es/senpy/senpy/badges/master/build.svg
:target: https://lab.cluster.gsi.dit.upm.es/senpy/senpy/commits/master
.. image:: https://lab.cluster.gsi.dit.upm.es/senpy/senpy/badges/master/coverage.svg
:target: https://lab.cluster.gsi.dit.upm.es/senpy/senpy/commits/master
.. image:: https://img.shields.io/pypi/l/requests.svg
:target: https://lab.cluster.gsi.dit.upm.es/senpy/senpy/
Senpy is a framework for sentiment and emotion analysis services.
Services built with senpy are interchangeable and easy to use because they share a common :doc:`apischema`.
It also simplifies service development.
.. image:: senpy-architecture.png
:width: 100%
:align: center
Contents:
.. toctree::
:caption: Learn more about senpy:
:maxdepth: 2
senpy
installation
demo
usage
apischema
api
schema
plugins
conversion
about
demo
:maxdepth: 2

View File

@@ -1,16 +1,6 @@
Installation
------------
The stable version can be used in two ways: as a system/user library through pip, or as a docker image.
The docker image is the recommended way because it is self-contained and isolated from the system, which means:
* Downloading and using it is just one command
* All dependencies are included
* It is OS-independent (MacOS, Windows, GNU/Linux)
* Several versions may coexist in the same machine without additional virtual environments
Additionally, you may create your own docker image with your custom plugins, ready to be used by others.
The stable version can be installed in three ways.
Through PIP
***********
@@ -32,41 +22,6 @@ If you want to install senpy globally, use sudo instead of the ``--user`` flag.
Docker Image
************
Build the image or use the pre-built one:
Build the image or use the pre-built one: ``docker run -ti -p 5000:5000 gsiupm/senpy --host 0.0.0.0 --default-plugins``.
.. code:: bash
docker run -ti -p 5000:5000 gsiupm/senpy --host 0.0.0.0 --default-plugins
To add custom plugins, use a docker volume:
.. code:: bash
docker run -ti -p 5000:5000 -v <PATH OF PLUGINS>:/plugins gsiupm/senpy --host 0.0.0.0 --default-plugins -f /plugins
Python 2
........
There is a Senpy version for python2 too:
.. code:: bash
docker run -ti -p 5000:5000 gsiupm/senpy:python2.7 --host 0.0.0.0 --default-plugins
Alias
.....
If you are using the docker approach regularly, it is advisable to use a script or an alias to simplify your executions:
.. code:: bash
alias senpy='docker run --rm -ti -p 5000:5000 -v $PWD:/senpy-plugins gsiupm/senpy --default-plugins'
Now, you may run senpy from any folder in your computer like so:
.. code:: bash
senpy --version
To add custom plugins, add a volume and tell senpy where to find the plugins: ``docker run -ti -p 5000:5000 -v <PATH OF PLUGINS>:/plugins gsiupm/senpy --host 0.0.0.0 --default-plugins -f /plugins``

View File

@@ -2,36 +2,27 @@ Developing new plugins
----------------------
This document describes how to develop a new analysis plugin. For an example of conversion plugins, see :doc:`conversion`.
A more step-by-step tutorial with slides is available `here <https://lab.cluster.gsi.dit.upm.es/senpy/senpy-tutorial>`__
Each plugin represents a different analysis process.There are two types of files that are needed by senpy for loading a plugin:
.. contents:: :local:
- Definition file, has the ".senpy" extension.
- Code file, is a python file.
What is a plugin?
=================
A plugin is a program that, given a text, will add annotations to it.
In practice, a plugin consists of at least two files:
- Definition file: a `.senpy` file that describes the plugin (e.g. what input parameters it accepts, what emotion model it uses).
- Python module: the actual code that will add annotations to each input.
This separation allows us to deploy plugins that use the same code but employ different parameters.
This separation will allow us to deploy plugins that use the same code but employ different parameters.
For instance, one could use the same classifier and processing in several plugins, but train with different datasets.
This scenario is particularly useful for evaluation purposes.
The only limitation is that the name of each plugin needs to be unique.
Plugin Definition files
=======================
Plugins Definitions
===================
The definition file contains all the attributes of the plugin, and can be written in YAML or JSON.
When the server is launched, it will recursively search for definition files in the plugin folder (the current folder, by default).
The most important attributes are:
* **name**: unique name that senpy will use internally to identify the plugin.
* **module**: indicates the module that contains the plugin code, which will be automatically loaded by senpy.
* **version**
* extra_params: to add parameters to the senpy API when this plugin is requested. Those parameters may be required, and have aliased names. For instance:
* extra_params: used to specify parameters that the plugin accepts that are not already part of the senpy API. Those parameters may be required, and have aliased names. For instance:
.. code:: yaml
@@ -77,28 +68,10 @@ The basic methods in a plugin are:
* __init__
* activate: used to load memory-hungry resources
* deactivate: used to free up resources
* analyse_entry: called in every user requests. It takes two parameters: ``Entry``, the entry object, and ``params``, the parameters supplied by the user. It should yield one or more ``Entry`` objects.
* analyse_entry: called in every user requests. It takes in the parameters supplied by a user and should yield one or more ``Entry`` objects.
Plugins are loaded asynchronously, so don't worry if the activate method takes too long. The plugin will be marked as activated once it is finished executing the method.
Entries
=======
Entries are objects that can be annotated.
By default, entries are `NIF contexts <http://persistence.uni-leipzig.org/nlp2rdf/ontologies/nif-core/nif-core.html>`_ represented in JSON-LD format.
Annotations are added to the object like this:
.. code:: python
entry = Entry()
entry.vocabulary__annotationName = 'myvalue'
entry['vocabulary:annotationName'] = 'myvalue'
entry['annotationNameURI'] = 'myvalue'
Where vocabulary is one of the prefixes defined in the default senpy context, and annotationURI is a full URI.
The value may be any valid JSON-LD dictionary.
For simplicity, senpy includes a series of models by default in the ``senpy.models`` module.
Example plugin
==============
@@ -115,7 +88,7 @@ The definition file would look like this:
module: helloworld
version: 0.0
threshold: 10
description: Hello World
Now, in a file named ``helloworld.py``:
@@ -124,11 +97,11 @@ Now, in a file named ``helloworld.py``:
#!/bin/env python
#helloworld.py
from senpy.plugins import AnalysisPlugin
from senpy.plugins import SenpyPlugin
from senpy.models import Sentiment
class HelloWorld(AnalysisPlugin):
class HelloWorld(SenpyPlugin):
def analyse_entry(entry, params):
'''Basically do nothing with each entry'''
@@ -141,112 +114,15 @@ Now, in a file named ``helloworld.py``:
entry.sentiments.append(sentiment)
yield entry
The complete code of the example plugin is available `here <https://lab.cluster.gsi.dit.upm.es/senpy/plugin-prueba>`__.
Loading data and files
======================
Most plugins will need access to files (dictionaries, lexicons, etc.).
It is good practice to specify the paths of these files in the plugin configuration, so the same code can be reused with different resources.
.. code:: yaml
name: dictworld
module: dictworld
dictionary_path: <PATH OF THE FILE>
The path can be either absolute, or relative.
From absolute paths
???????????????????
Absolute paths (such as ``/data/dictionary.csv`` are straightfoward:
.. code:: python
with open(os.path.join(self.dictionary_path) as f:
...
From relative paths
???????????????????
Since plugins are loading dynamically, relative paths will refer to the current working directory.
Instead, what you usually want is to load files *relative to the plugin source folder*, like so:
::
.
..
plugin.senpy
plugin.py
dictionary.csv
For this, we need to first get the path of your source folder first, like so:
.. code:: python
import os
root = os.path.realpath(__file__)
with open(os.path.join(root, self.dictionary_path) as f:
...
Docker image
============
Add the following dockerfile to your project to generate a docker image with your plugin:
.. code:: dockerfile
FROM gsiupm/senpy:0.8.8
This will copy your source folder to the image, and install all dependencies.
Now, to build an image:
.. code:: shell
docker build . -t gsiupm/exampleplugin
And you can run it with:
.. code:: shell
docker run -p 5000:5000 gsiupm/exampleplugin
If the plugin non-source files (:ref:`loading data and files`), the recommended way is to use absolute paths.
Data can then be mounted in the container or added to the image.
The former is recommended for open source plugins with licensed resources, whereas the latter is the most convenient and can be used for private images.
Mounting data:
.. code:: bash
docker run -v $PWD/data:/data gsiupm/exampleplugin
Adding data to the image:
.. code:: dockerfile
FROM gsiupm/senpy:0.8.8
COPY data /
F.A.Q.
======
What annotations can I use?
???????????????????????????
You can add almost any annotation to an entry.
The most common use cases are covered in the :doc:`apischema`.
Why does the analyse function yield instead of return?
??????????????????????????????????????????????????????
This is so that plugins may add new entries to the response or filter some of them.
For instance, a `context detection` plugin may add a new entry for each context in the original entry.
On the other hand, a conversion plugin may leave out those entries that do not contain relevant information.
On the other hand, a conveersion plugin may leave out those entries that do not contain relevant information.
If I'm using a classifier, where should I train it?
@@ -256,9 +132,9 @@ Training a classifier can be time time consuming. To avoid running the training
.. code:: python
from senpy.plugins import ShelfMixin, AnalysisPlugin
from senpy.plugins import ShelfMixin, SenpyPlugin
class MyPlugin(ShelfMixin, AnalysisPlugin):
class MyPlugin(ShelfMixin, SenpyPlugin):
def train(self):
''' Code to train the classifier
'''
@@ -275,16 +151,12 @@ Training a classifier can be time time consuming. To avoid running the training
def deactivate(self):
self.close()
You can specify a 'shelf_file' in your .senpy file. By default the ShelfMixin creates a file based on the plugin name and stores it in that plugin's folder.
You can speficy a 'shelf_file' in your .senpy file. By default the ShelfMixin creates a file based on the plugin name and stores it in that plugin's folder.
Shelves may get corrupted if the plugin exists unexpectedly.
A corrupt shelf prevents the plugin from loading.
If you do not care about the pickle, you can force your plugin to remove the corrupted file and load anyway, set the 'force_shelf' to True in your .senpy file.
I want to implement my service as a plugin, How i can do it?
????????????????????????????????????????????????????????????
How can I turn an external service into a plugin?
?????????????????????????????????????????????????
This example ilustrate how to implement a plugin that accesses the Sentiment140 service.
This example ilustrate how to implement the Sentiment140 service as a plugin in senpy
.. code:: python
@@ -318,30 +190,26 @@ This example ilustrate how to implement a plugin that accesses the Sentiment140
yield entry
Can my plugin require additional parameters from the user?
??????????????????????????????????????????????????????????
Where can I define extra parameters to be introduced in the request to my plugin?
?????????????????????????????????????????????????????????????????????????????????
You can add extra parameters in the definition file under the attribute ``extra_params``.
It takes a dictionary, where the keys are the name of the argument/parameter, and the value has the following fields:
You can add these parameters in the definition file under the attribute "extra_params" : "{param_name}". The name of the parameter has new attributes-value pairs. The basic attributes are:
* aliases: the different names which can be used in the request to use the parameter.
* required: if set to true, users need to provide this parameter unless a default is set.
* options: the different acceptable values of the parameter (i.e. an enum). If set, the value provided must match one of the options.
* default: the default value of the parameter, if none is provided in the request.
* required: this option is a boolean and indicates if the parameters is binding in operation plugin.
* options: the different values of the paremeter.
* default: the default value of the parameter, this is useful in case the paremeter is required and you want to have a default value.
.. code:: python
extra_params
language:
aliases:
- language
- lang
- l
required: true,
options:
- es
- en
default: es
"extra_params": {
"language": {
"aliases": ["language", "l"],
"required": true,
"options": ["es","en"],
"default": "es"
}
}
This example shows how to introduce a parameter associated with language.
The extraction of this paremeter is used in the analyse method of the Plugin interface.
@@ -373,6 +241,7 @@ Additionally, with the ``--pdb`` option you will be dropped into a pdb post mort
senpy --pdb
Where can I find more code examples?
????????????????????????????????????

View File

@@ -1,2 +1 @@
sphinxcontrib-httpdomain>=1.4
nbsphinx

74
docs/schema.rst Normal file
View File

@@ -0,0 +1,74 @@
Schema Examples
===============
All the examples in this page use the :download:`the main schema <_static/schemas/definitions.json>`.
Simple NIF annotation
---------------------
Description
...........
This example covers the basic example in the NIF documentation: `<http://persistence.uni-leipzig.org/nlp2rdf/ontologies/nif-core/nif-core.html>`_.
Representation
..............
.. literalinclude:: examples/example-basic.json
:language: json-ld
Sentiment Analysis
---------------------
Description
...........
Representation
..............
.. literalinclude:: examples/example-sentiment.json
:emphasize-lines: 5-10,25-33
:language: json-ld
Suggestion Mining
-----------------
Description
...........
Representation
..............
.. literalinclude:: examples/example-suggestion.json
:emphasize-lines: 5-8,22-27
:language: json-ld
Emotion Analysis
----------------
Description
...........
Representation
..............
.. literalinclude:: examples/example-emotion.json
:language: json-ld
:emphasize-lines: 5-8,25-37
Named Entity Recognition
------------------------
Description
...........
Representation
..............
.. literalinclude:: examples/example-ner.json
:emphasize-lines: 5-8,19-34
:language: json-ld
Complete example
----------------
Description
...........
This example covers all of the above cases, integrating all the annotations in the same document.
Representation
..............
.. literalinclude:: examples/example-complete.json
:language: json-ld

Binary file not shown.

Before

Width:  |  Height:  |  Size: 122 KiB

After

Width:  |  Height:  |  Size: 65 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 49 KiB

After

Width:  |  Height:  |  Size: 79 KiB

View File

@@ -1,38 +1,20 @@
What is Senpy?
--------------
Web services can get really complex: data validation, user interaction, formatting, logging., etc.
The figure below summarizes the typical features in an analysis service.
Senpy implements all the common blocks, so developers can focus on what really matters: great analysis algorithms that solve real problems.
Senpy is an open source reference implementation of a linked data model for sentiment and emotion analysis services based on the vocabularies NIF, Marl and Onyx.
.. image:: senpy-framework.png
:width: 60%
:align: center
The overall goal of the reference implementation Senpy is easing the adoption of the proposed linked data model for sentiment and emotion analysis services, so that services from different providers become interoperable. With this aim, the design of the reference implementation has focused on its extensibility and reusability.
A modular approach allows organizations to replace individual components with custom ones developed in-house. Furthermore, organizations can benefit from reusing prepackages modules that provide advanced functionalities, such as algorithms for sentiment and emotion analysis, linked data publication or emotion and sentiment mapping between different providers.
Senpy for end users
===================
Specifications
==============
All services built using senpy share a common interface.
This allows users to use them (almost) interchangeably.
Senpy comes with a :ref:`built-in client`.
The model used in Senpy is based on the following specifications:
Senpy for service developers
============================
Senpy is a framework that turns your sentiment or emotion analysis algorithm into a full blown semantic service.
Senpy takes care of:
* Interfacing with the user: parameter validation, error handling.
* Formatting: JSON-LD, Turtle/n-triples input and output, or simple text input
* Linked Data: senpy results are semantically annotated, using a series of well established vocabularies, and sane default URIs.
* User interface: a web UI where users can explore your service and test different settings
* A client to interact with the service. Currently only available in Python.
Sharing your sentiment analysis with the world has never been easier!
Check out the :doc:`plugins` if you have developed an analysis algorithm (e.g. sentiment analysis) and you want to publish it as a service.
* Marl, a vocabulary designed to annotate and describe subjetive opinions expressed on the web or in information systems.
* Onyx, which is built one the same principles as Marl to annotate and describe emotions, and provides interoperability with Emotion Markup Language.
* NIF 2.0, which defines a semantic format and APO for improving interoperability among natural language processing services
Architecture
============
@@ -47,5 +29,7 @@ Senpy proposes a modular and dynamic architecture that allows:
The framework consists of two main modules: Senpy core, which is the building block of the service, and Senpy plugins, which consist of the analysis algorithm. The next figure depicts a simplified version of the processes involved in an analysis with the Senpy framework.
.. image:: senpy-architecture.png
:width: 100%
:height: 400px
:width: 800px
:scale: 100 %
:align: center

View File

@@ -1,58 +0,0 @@
Server
======
The senpy server is launched via the `senpy` command:
.. code:: text
usage: senpy [-h] [--level logging_level] [--debug] [--default-plugins]
[--host HOST] [--port PORT] [--plugins-folder PLUGINS_FOLDER]
[--only-install]
Run a Senpy server
optional arguments:
-h, --help show this help message and exit
--level logging_level, -l logging_level
Logging level
--debug, -d Run the application in debug mode
--default-plugins Load the default plugins
--host HOST Use 0.0.0.0 to accept requests from any host.
--port PORT, -p PORT Port to listen on.
--plugins-folder PLUGINS_FOLDER, -f PLUGINS_FOLDER
Where to look for plugins.
--only-install, -i Do not run a server, only install plugin dependencies
When launched, the server will recursively look for plugins in the specified plugins folder (the current working directory by default).
For every plugin found, it will download its dependencies, and try to activate it.
The default server includes a playground and an endpoint with all plugins found.
Let's run senpy with the default plugins:
.. code:: bash
senpy -f . --default-plugins
Now go to `http://localhost:5000 <http://localhost:5000>`_, you should be greeted by the senpy playground:
.. image:: senpy-playground.png
:width: 100%
:alt: Playground
The playground is a user-friendly way to test your plugins, but you can always use the service directly: `http://localhost:5000/api?input=hello <http://localhost:5000/api?input=hello>`_.
By default, senpy will listen only on the `127.0.0.1` address.
That means you can only access the API from your (or localhost).
You can listen on a different address using the `--host` flag (e.g., 0.0.0.0).
The default port is 5000.
You can change it with the `--port` flag.
For instance, to accept connections on port 6000 on any interface:
.. code:: bash
senpy --host 0.0.0.0 --port 6000
For more options, see the `--help` page.

View File

@@ -1,15 +1,80 @@
Usage
-----
First of all, you need to install the package.
See :doc:`installation` for instructions.
Once installed, the `senpy` command should be available.
The easiest and recommended way is to just use the command-line tool to load your plugins and launch the server.
.. toctree::
:maxdepth: 1
.. code:: bash
server
SenpyClientUse
commandline
senpy
Or, alternatively:
.. code:: bash
python -m senpy
This will create a server with any modules found in the current path.
Useful command-line options
===========================
In case you want to load modules, which are located in different folders under the root folder, use the next option.
.. code:: bash
python -m senpy -f .
The default port used by senpy is 5000, but you can change it using the option `--port`.
.. code:: bash
python -m senpy --port 8080
Also, the host can be changed where senpy is deployed. The default value is `127.0.0.1`.
.. code:: bash
python -m senpy --host 0.0.0.0
For more options, see the `--help` page.
Alternatively, you can use the modules included in senpy to build your own application.
Senpy server
============
Once the server is launched, there is a basic endpoint in the server, which provides a playground to use the plugins that have been loaded.
In case you want to know the different endpoints of the server, there is more information available in the NIF API section_.
CLI
===
This video shows how to use senpy through command-line tool.
https://asciinema.org/a/9uwef1ghkjk062cw2t4mhzpyk
Request example in python
=========================
This example shows how to make a request to the default plugin:
.. code:: python
from senpy.client import Client
c = Client('http://127.0.0.1:5000/api/')
r = c.analyse('hello world')
for entry in r.entries:
print('{} -> {}'.format(entry.text, entry.emotions))
.. _section: http://senpy.readthedocs.org/en/latest/api.html
Conversion
==========
See :doc:`conversion`

View File

@@ -1,8 +0,0 @@
Vocabularies and model
======================
The model used in Senpy is based on the following vocabularies:
* Marl, a vocabulary designed to annotate and describe subjetive opinions expressed on the web or in information systems.
* Onyx, which is built one the same principles as Marl to annotate and describe emotions, and provides interoperability with Emotion Markup Language.
* NIF 2.0, which defines a semantic format and APO for improving interoperability among natural language processing services

View File

@@ -1,7 +0,0 @@
Deploy senpy to a kubernetes cluster.
Usage:
```
kubectl apply -f . -n senpy
```

View File

@@ -1,26 +0,0 @@
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: senpy-latest
spec:
replicas: 1
template:
metadata:
labels:
role: senpy-latest
app: test
spec:
containers:
- name: senpy-latest
image: gsiupm/senpy:latest
imagePullPolicy: Always
args:
- "--default-plugins"
resources:
limits:
memory: "512Mi"
cpu: "1000m"
ports:
- name: web
containerPort: 5000

View File

@@ -1,14 +0,0 @@
---
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
name: senpy-ingress
spec:
rules:
- host: latest.senpy.cluster.gsi.dit.upm.es
http:
paths:
- path: /
backend:
serviceName: senpy-latest
servicePort: 5000

View File

@@ -1,12 +0,0 @@
---
apiVersion: v1
kind: Service
metadata:
name: senpy-latest
spec:
type: ClusterIP
ports:
- port: 5000
protocol: TCP
selector:
role: senpy-latest

View File

@@ -1,8 +1,7 @@
Flask>=0.10.1
requests>=2.4.1
tornado>=4.4.3
gevent>=1.1rc4
PyLD>=0.6.5
nltk
six
future
jsonschema

View File

@@ -22,15 +22,35 @@ the server.
from flask import Flask
from senpy.extensions import Senpy
from gevent.wsgi import WSGIServer
from gevent.monkey import patch_all
import logging
import os
import sys
import argparse
import senpy
patch_all(thread=False)
SERVER_PORT = os.environ.get("PORT", 5000)
def info(type, value, tb):
if hasattr(sys, 'ps1') or not sys.stderr.isatty():
# we are in interactive mode or we don't have a tty-like
# device, so we call the default hook
sys.__excepthook__(type, value, tb)
else:
import traceback
import pdb
# we are NOT in interactive mode, print the exception...
traceback.print_exception(type, value, tb)
print
# ...then start the debugger in post-mortem mode.
# pdb.pm() # deprecated
pdb.post_mortem(tb) # more "modern"
def main():
parser = argparse.ArgumentParser(description='Run a Senpy server')
parser.add_argument(
@@ -74,38 +94,28 @@ def main():
action='store_true',
default=False,
help='Do not run a server, only install plugin dependencies')
parser.add_argument(
'--threaded',
action='store_false',
default=True,
help='Run a threaded server')
parser.add_argument(
'--version',
'-v',
action='store_true',
default=False,
help='Output the senpy version and exit')
args = parser.parse_args()
if args.version:
print('Senpy version {}'.format(senpy.__version__))
exit(1)
logging.basicConfig()
rl = logging.getLogger()
rl.setLevel(getattr(logging, args.level))
app = Flask(__name__)
app.debug = args.debug
if args.debug:
sys.excepthook = info
sp = Senpy(app, args.plugins_folder, default_plugins=args.default_plugins)
sp.install_deps()
if args.only_install:
sp.install_deps()
return
sp.activate_all()
print('Senpy version {}'.format(senpy.__version__))
print('Server running on port %s:%d. Ctrl+C to quit' % (args.host,
args.port))
app.run(args.host,
args.port,
threaded=args.threaded,
debug=app.debug)
http_server = WSGIServer((args.host, args.port), app)
try:
print('Senpy version {}'.format(senpy.__version__))
print('Server running on port %s:%d. Ctrl+C to quit' % (args.host,
args.port))
http_server.serve_forever()
except KeyboardInterrupt:
print('Bye!')
http_server.stop()
sp.deactivate_all()

View File

@@ -1,55 +1,38 @@
from future.utils import iteritems
from .models import Error, Results, Entry, from_string
from .models import Error
import logging
logger = logging.getLogger(__name__)
API_PARAMS = {
"algorithm": {
"aliases": ["algorithms", "a", "algo"],
"aliases": ["algorithm", "a", "algo"],
"required": False,
"description": ("Algorithms that will be used to process the request."
"It may be a list of comma-separated names."),
},
"expanded-jsonld": {
"@id": "expanded-jsonld",
"aliases": ["expanded"],
"required": True,
"default": 0
},
"with_parameters": {
"aliases": ['withparameters',
'with-parameters'],
"options": "boolean",
"default": False,
"required": True
},
"plugin_type": {
"@id": "pluginType",
"description": 'What kind of plugins to list',
"aliases": ["pluginType"],
"required": True,
"default": "analysisPlugin"
},
"outformat": {
"@id": "outformat",
"aliases": ["o"],
"aliases": ["outformat", "o"],
"default": "json-ld",
"required": True,
"options": ["json-ld", "turtle"],
},
"help": {
"@id": "help",
"description": "Show additional help to know more about the possible parameters",
"aliases": ["h"],
"expanded-jsonld": {
"@id": "expanded-jsonld",
"aliases": ["expanded", "expanded-jsonld"],
"required": True,
"options": "boolean",
"default": False
"default": 0
},
"emotionModel": {
"@id": "emotionModel",
"aliases": ["emoModel"],
"aliases": ["emotionModel", "emoModel"],
"required": False
},
"plugin_type": {
"@id": "pluginType",
"description": 'What kind of plugins to list',
"aliases": ["pluginType", "plugin_type"],
"required": True,
"default": "analysisPlugin"
},
"conversion": {
"@id": "conversion",
"description": "How to show the elements that have (not) been converted",
@@ -61,16 +44,15 @@ API_PARAMS = {
WEB_PARAMS = {
"inHeaders": {
"aliases": ["headers"],
"aliases": ["inHeaders", "headers"],
"required": True,
"default": False,
"options": "boolean"
"default": "0"
},
}
CLI_PARAMS = {
"plugin_folder": {
"aliases": ["folder"],
"aliases": ["plugin_folder", "folder"],
"required": True,
"default": "."
},
@@ -79,71 +61,64 @@ CLI_PARAMS = {
NIF_PARAMS = {
"input": {
"@id": "input",
"aliases": ["i"],
"aliases": ["i", "input"],
"required": True,
"help": "Input text"
},
"informat": {
"@id": "informat",
"aliases": ["f", "informat"],
"required": False,
"default": "text",
"options": ["turtle", "text"],
},
"intype": {
"@id": "intype",
"aliases": ["t"],
"aliases": ["intype", "t"],
"required": False,
"default": "direct",
"options": ["direct", "url", "file"],
},
"informat": {
"@id": "informat",
"aliases": ["f"],
"required": False,
"default": "text",
"options": ["turtle", "text", "json-ld"],
},
"language": {
"@id": "language",
"aliases": ["l"],
"aliases": ["language", "l"],
"required": False,
},
"prefix": {
"@id": "prefix",
"aliases": ["p"],
"aliases": ["prefix", "p"],
"required": True,
"default": "",
},
"urischeme": {
"@id": "urischeme",
"aliases": ["u"],
"aliases": ["urischeme", "u"],
"required": False,
"default": "RFC5147String",
"options": "RFC5147String"
}
},
}
def parse_params(indict, *specs):
if not specs:
specs = [NIF_PARAMS]
logger.debug("Parsing: {}\n{}".format(indict, specs))
def parse_params(indict, spec=NIF_PARAMS):
logger.debug("Parsing: {}\n{}".format(indict, spec))
outdict = indict.copy()
wrong_params = {}
for spec in specs:
for param, options in iteritems(spec):
if param[0] != "@": # Exclude json-ld properties
for alias in options.get("aliases", []):
# Replace each alias with the correct name of the parameter
if alias in indict and alias is not param:
outdict[param] = indict[alias]
del indict[alias]
continue
if param not in outdict:
if options.get("required", False) and "default" not in options:
wrong_params[param] = spec[param]
else:
if "default" in options:
outdict[param] = options["default"]
elif "options" in spec[param]:
if spec[param]["options"] == "boolean":
outdict[param] = outdict[param] in [None, True, 'true', '1']
elif outdict[param] not in spec[param]["options"]:
wrong_params[param] = spec[param]
for param, options in iteritems(spec):
if param[0] != "@": # Exclude json-ld properties
for alias in options.get("aliases", []):
if alias in indict:
outdict[param] = indict[alias]
if param not in outdict:
if options.get("required", False) and "default" not in options:
wrong_params[param] = spec[param]
else:
if "default" in options:
outdict[param] = options["default"]
else:
if "options" in spec[param] and \
outdict[param] not in spec[param]["options"]:
wrong_params[param] = spec[param]
if wrong_params:
logger.debug("Error parsing: %s", wrong_params)
message = Error(
@@ -153,30 +128,4 @@ def parse_params(indict, *specs):
errors={param: error
for param, error in iteritems(wrong_params)})
raise message
if 'algorithm' in outdict and not isinstance(outdict['algorithm'], list):
outdict['algorithm'] = outdict['algorithm'].split(',')
return outdict
def get_extra_params(request, plugin=None):
params = request.parameters.copy()
if plugin:
extra_params = parse_params(params, plugin.get('extra_params', {}))
params.update(extra_params)
return params
def parse_call(params):
'''Return a results object based on the parameters used in a call/request.
'''
params = parse_params(params, NIF_PARAMS)
if params['informat'] == 'text':
results = Results()
entry = Entry(nif__isString=params['input'])
results.entries.append(entry)
elif params['informat'] == 'json-ld':
results = from_string(params['input'], cls=Results)
else:
raise NotImplemented('Informat {} is not implemented'.format(params['informat']))
results.parameters = params
return results

View File

@@ -19,13 +19,12 @@ Blueprints for Senpy
"""
from flask import (Blueprint, request, current_app, render_template, url_for,
jsonify)
from .models import Error, Response, Help, Plugins, read_schema
from . import api
from .models import Error, Response, Plugins, read_schema
from .api import WEB_PARAMS, API_PARAMS, parse_params
from .version import __version__
from functools import wraps
import logging
import json
logger = logging.getLogger(__name__)
@@ -75,33 +74,33 @@ def basic_api(f):
@wraps(f)
def decorated_function(*args, **kwargs):
raw_params = get_params(request)
headers = {'X-ORIGINAL-PARAMS': json.dumps(raw_params)}
headers = {'X-ORIGINAL-PARAMS': raw_params}
# Get defaults
web_params = parse_params({}, spec=WEB_PARAMS)
api_params = parse_params({}, spec=API_PARAMS)
outformat = 'json-ld'
try:
print('Getting request:')
print(request)
params = api.parse_params(raw_params, api.WEB_PARAMS, api.API_PARAMS)
if hasattr(request, 'parameters'):
request.parameters.update(params)
web_params = parse_params(raw_params, spec=WEB_PARAMS)
api_params = parse_params(raw_params, spec=API_PARAMS)
if hasattr(request, 'params'):
request.params.update(api_params)
else:
request.parameters = params
request.params = api_params
response = f(*args, **kwargs)
except Error as ex:
response = ex
response.parameters = params
logger.error(ex)
if current_app.debug:
raise
in_headers = params['inHeaders']
expanded = params['expanded-jsonld']
outformat = params['outformat']
in_headers = web_params['inHeaders'] != "0"
expanded = api_params['expanded-jsonld']
outformat = api_params['outformat']
return response.flask(
in_headers=in_headers,
headers=headers,
prefix=url_for('.api_root', _external=True),
prefix=url_for('.api', _external=True),
context_uri=url_for('api.context',
entity=type(response).__name__,
_external=True),
@@ -113,22 +112,16 @@ def basic_api(f):
@api_blueprint.route('/', methods=['POST', 'GET'])
@basic_api
def api_root():
if request.parameters['help']:
dic = dict(api.API_PARAMS, **api.NIF_PARAMS)
response = Help(parameters=dic)
return response
else:
req = api.parse_call(request.parameters)
response = current_app.senpy.analyse(req)
return response
def api():
response = current_app.senpy.analyse(**request.params)
return response
@api_blueprint.route('/plugins/', methods=['POST', 'GET'])
@basic_api
def plugins():
sp = current_app.senpy
ptype = request.parameters.get('plugin_type')
ptype = request.params.get('plugin_type')
plugins = sp.filter_plugins(plugin_type=ptype)
dic = Plugins(plugins=list(plugins.values()))
return dic

View File

@@ -1,7 +1,7 @@
import sys
from .models import Error
from .api import parse_params, CLI_PARAMS
from .extensions import Senpy
from . import api
def argv_to_dict(argv):
@@ -13,27 +13,27 @@ def argv_to_dict(argv):
if argv[i][0] == '-':
key = argv[i].strip('-')
value = argv[i + 1] if len(argv) > i + 1 else None
if not value or value[0] == '-':
cli_dict[key] = True
if value and value[0] == '-':
cli_dict[key] = ""
else:
cli_dict[key] = value
return cli_dict
def parse_cli(argv):
cli_dict = argv_to_dict(argv)
cli_params = parse_params(cli_dict, spec=CLI_PARAMS)
return cli_params, cli_dict
def main_function(argv):
'''This is the method for unit testing
'''
params = api.parse_params(argv_to_dict(argv),
api.CLI_PARAMS,
api.API_PARAMS,
api.NIF_PARAMS)
plugin_folder = params['plugin_folder']
cli_params, cli_dict = parse_cli(argv)
plugin_folder = cli_params['plugin_folder']
sp = Senpy(default_plugins=False, plugin_folder=plugin_folder)
request = api.parse_call(params)
algos = request.parameters.get('algorithm', sp.plugins.keys())
for algo in algos:
sp.activate_plugin(algo)
res = sp.analyse(request)
sp.activate_all(sync=True)
res = sp.analyse(**cli_dict)
return res

View File

@@ -1,7 +1,6 @@
import requests
import logging
from . import models
from .plugins import default_plugin_type
logger = logging.getLogger(__name__)
@@ -13,15 +12,12 @@ class Client(object):
def analyse(self, input, method='GET', **kwargs):
return self.request('/', method=method, input=input, **kwargs)
def plugins(self, ptype=default_plugin_type):
resp = self.request(path='/plugins', plugin_type=ptype).plugins
return {p.name: p for p in resp}
def request(self, path=None, method='GET', **params):
url = '{}{}'.format(self.endpoint, path)
response = requests.request(method=method, url=url, params=params)
try:
resp = models.from_dict(response.json())
resp.validate(resp)
except Exception as ex:
logger.error(('There seems to be a problem with the response:\n'
'\tURL: {url}\n'

View File

@@ -5,18 +5,24 @@ It orchestrates plugin (de)activation and analysis.
from future import standard_library
standard_library.install_aliases()
from . import plugins, api
from . import plugins
from .plugins import SenpyPlugin
from .models import Error
from .models import Error, Entry, Results
from .blueprints import api_blueprint, demo_blueprint, ns_blueprint
from .api import API_PARAMS, NIF_PARAMS, parse_params
from threading import Thread
from functools import partial
import os
import copy
import fnmatch
import inspect
import sys
import importlib
import logging
import traceback
import yaml
import pip
logger = logging.getLogger(__name__)
@@ -72,85 +78,74 @@ class Senpy(object):
else:
logger.debug("Not a folder: %s", folder)
def _get_plugins(self, request):
if not self.analysis_plugins:
def _find_plugin(self, params):
api_params = parse_params(params, spec=API_PARAMS)
algo = None
if "algorithm" in api_params and api_params["algorithm"]:
algo = api_params["algorithm"]
elif self.plugins:
algo = self.default_plugin and self.default_plugin.name
if not algo:
raise Error(
status=404,
message=("No plugins found."
" Please install one."))
algos = request.parameters.get('algorithm', None)
if not algos:
if self.default_plugin:
algos = [self.default_plugin.name, ]
else:
raise Error(
status=404,
message="No default plugin found, and None provided")
" Please install one.").format(algo))
if algo not in self.plugins:
logger.debug(("The algorithm '{}' is not valid\n"
"Valid algorithms: {}").format(algo,
self.plugins.keys()))
raise Error(
status=404,
message="The algorithm '{}' is not valid".format(algo))
plugins = list()
for algo in algos:
if algo not in self.plugins:
logger.debug(("The algorithm '{}' is not valid\n"
"Valid algorithms: {}").format(algo,
self.plugins.keys()))
raise Error(
status=404,
message="The algorithm '{}' is not valid".format(algo))
plugins.append(self.plugins[algo])
return plugins
if not self.plugins[algo].is_activated:
logger.debug("Plugin not activated: {}".format(algo))
raise Error(
status=400,
message=("The algorithm '{}'"
" is not activated yet").format(algo))
return self.plugins[algo]
def _process_entries(self, entries, req, plugins):
"""
Recursively process the entries with the first plugin in the list, and pass the results
to the rest of the plugins.
"""
if not plugins:
for i in entries:
yield i
return
plugin = plugins[0]
self._activate(plugin) # Make sure the plugin is activated
specific_params = api.get_extra_params(req, plugin)
req.analysis.append({'plugin': plugin,
'parameters': specific_params})
results = plugin.analyse_entries(entries, specific_params)
for i in self._process_entries(results, req, plugins[1:]):
yield i
def _get_params(self, params, plugin):
nif_params = parse_params(params, spec=NIF_PARAMS)
extra_params = plugin.get('extra_params', {})
specific_params = parse_params(params, spec=extra_params)
nif_params.update(specific_params)
return nif_params
def install_deps(self):
for plugin in self.filter_plugins(is_activated=True):
plugins.install_deps(plugin)
def _get_entries(self, params):
entry = None
if params['informat'] == 'text':
entry = Entry(text=params['input'])
else:
raise NotImplemented('Only text input format implemented')
yield entry
def analyse(self, request):
"""
Main method that analyses a request, either from CLI or HTTP.
It takes a processed request, provided by the user, as returned
by api.parse_call().
"""
logger.debug("analysing request: {}".format(request))
def analyse(self, **api_params):
logger.debug("analysing with params: {}".format(api_params))
plugin = self._find_plugin(api_params)
nif_params = self._get_params(api_params, plugin)
resp = Results()
if 'with_parameters' in api_params:
resp.parameters = nif_params
try:
entries = request.entries
request.entries = []
plugins = self._get_plugins(request)
results = request
for i in self._process_entries(entries, results, plugins):
results.entries.append(i)
self.convert_emotions(results)
if 'with_parameters' not in results.parameters:
del results.parameters
logger.debug("Returning analysis result: {}".format(results))
except (Error, Exception) as ex:
if not isinstance(ex, Error):
msg = "Error during analysis: {} \n\t{}".format(ex,
traceback.format_exc())
ex = Error(message=msg, status=500)
entries = []
for i in self._get_entries(nif_params):
entries += list(plugin.analyse_entry(i, nif_params))
resp.entries = entries
self.convert_emotions(resp, plugin, nif_params)
resp.analysis.append(plugin.id)
logger.debug("Returning analysis result: {}".format(resp))
except Error as ex:
logger.exception('Error returning analysis result')
raise ex
results.analysis = [i['plugin'].id for i in results.analysis]
return results
resp = ex
except Exception as ex:
logger.exception('Error returning analysis result')
resp = Error(message=str(ex), status=500)
return resp
def _conversion_candidates(self, fromModel, toModel):
candidates = self.filter_plugins(plugin_type='emotionConversionPlugin')
candidates = self.filter_plugins(**{'@type': 'emotionConversionPlugin'})
for name, candidate in candidates.items():
for pair in candidate.onyx__doesConversion:
logging.debug(pair)
@@ -160,34 +155,30 @@ class Senpy(object):
# logging.debug('Found candidate: {}'.format(candidate))
yield candidate
def convert_emotions(self, resp):
def convert_emotions(self, resp, plugin, params):
"""
Conversion of all emotions in a response **in place**.
Conversion of all emotions in a response.
In addition to converting from one model to another, it has
to include the conversion plugin to the analysis list.
Needless to say, this is far from an elegant solution, but it works.
@todo refactor and clean up
"""
plugins = [i['plugin'] for i in resp.analysis]
params = resp.parameters
fromModel = plugin.get('onyx:usesEmotionModel', None)
toModel = params.get('emotionModel', None)
output = params.get('conversion', None)
logger.debug('Asked for model: {}'.format(toModel))
logger.debug('Analysis plugin uses model: {}'.format(fromModel))
if not toModel:
return
logger.debug('Asked for model: {}'.format(toModel))
output = params.get('conversion', None)
candidates = {}
for plugin in plugins:
try:
fromModel = plugin.get('onyx:usesEmotionModel', None)
candidates[plugin.id] = next(self._conversion_candidates(fromModel, toModel))
logger.debug('Analysis plugin {} uses model: {}'.format(plugin.id, fromModel))
except StopIteration:
e = Error(('No conversion plugin found for: '
'{} -> {}'.format(fromModel, toModel)))
e.original_response = resp
e.parameters = params
raise e
try:
candidate = next(self._conversion_candidates(fromModel, toModel))
except StopIteration:
e = Error(('No conversion plugin found for: '
'{} -> {}'.format(fromModel, toModel)))
e.original_response = resp
e.parameters = params
raise e
newentries = []
for i in resp.entries:
if output == "full":
@@ -195,10 +186,6 @@ class Senpy(object):
else:
newemotions = []
for j in i.emotions:
plugname = j['prov:wasGeneratedBy']
candidate = candidates[plugname]
resp.analysis.append({'plugin': candidate,
'parameters': params})
for k in candidate.convert(j, fromModel, toModel, params):
k.prov__wasGeneratedBy = candidate.id
if output == 'nested':
@@ -207,13 +194,13 @@ class Senpy(object):
i.emotions = newemotions
newentries.append(i)
resp.entries = newentries
resp.analysis.append(candidate.id)
@property
def default_plugin(self):
candidate = self._default
if not candidate:
candidates = self.filter_plugins(plugin_type='analysisPlugin',
is_activated=True)
candidates = self.filter_plugins(is_activated=True)
if len(candidates) > 0:
candidate = list(candidates.values())[0]
logger.debug("Default: {}".format(candidate))
@@ -226,42 +213,25 @@ class Senpy(object):
else:
self._default = self.plugins[value]
def activate_all(self, sync=True):
def activate_all(self, sync=False):
ps = []
for plug in self.plugins.keys():
ps.append(self.activate_plugin(plug, sync=sync))
return ps
def deactivate_all(self, sync=True):
def deactivate_all(self, sync=False):
ps = []
for plug in self.plugins.keys():
ps.append(self.deactivate_plugin(plug, sync=sync))
return ps
def _set_active(self, plugin, active=True, *args, **kwargs):
def _set_active_plugin(self, plugin_name, active=True, *args, **kwargs):
''' We're using a variable in the plugin itself to activate/deactive plugins.\
Note that plugins may activate themselves by setting this variable.
'''
plugin.is_activated = active
self.plugins[plugin_name].is_activated = active
def _activate(self, plugin):
success = False
with plugin._lock:
if plugin.is_activated:
return
try:
plugin.activate()
msg = "Plugin activated: {}".format(plugin.name)
logger.info(msg)
success = True
self._set_active(plugin, success)
except Exception as ex:
msg = "Error activating plugin {} - {} : \n\t{}".format(
plugin.name, ex, traceback.format_exc())
logger.error(msg)
raise Error(msg)
def activate_plugin(self, plugin_name, sync=True):
def activate_plugin(self, plugin_name, sync=False):
try:
plugin = self.plugins[plugin_name]
except KeyError:
@@ -270,17 +240,36 @@ class Senpy(object):
logger.info("Activating plugin: {}".format(plugin.name))
if sync or 'async' in plugin and not plugin.async:
self._activate(plugin)
else:
th = Thread(target=partial(self._activate, plugin))
th.start()
return th
def act():
success = False
try:
plugin.activate()
msg = "Plugin activated: {}".format(plugin.name)
logger.info(msg)
success = True
self._set_active_plugin(plugin_name, success)
except Exception as ex:
msg = "Error activating plugin {} - {} : \n\t{}".format(
plugin.name, ex, traceback.format_exc())
logger.error(msg)
raise Error(msg)
def _deactivate(self, plugin):
with plugin._lock:
if not plugin.is_activated:
return
if sync or 'async' in plugin and not plugin.async:
act()
else:
th = Thread(target=act)
th.start()
def deactivate_plugin(self, plugin_name, sync=False):
try:
plugin = self.plugins[plugin_name]
except KeyError:
raise Error(
message="Plugin not found: {}".format(plugin_name), status=404)
self._set_active_plugin(plugin_name, False)
def deact():
try:
plugin.deactivate()
logger.info("Plugin deactivated: {}".format(plugin.name))
@@ -289,21 +278,83 @@ class Senpy(object):
"Error deactivating plugin {}: {}".format(plugin.name, ex))
logger.error("Trace: {}".format(traceback.format_exc()))
def deactivate_plugin(self, plugin_name, sync=True):
try:
plugin = self.plugins[plugin_name]
except KeyError:
raise Error(
message="Plugin not found: {}".format(plugin_name), status=404)
self._set_active(plugin, False)
if sync or 'async' in plugin and not plugin.async:
self._deactivate(plugin)
deact()
else:
th = Thread(target=partial(self._deactivate, plugin))
th = Thread(target=deact)
th.start()
return th
@classmethod
def validate_info(cls, info):
return all(x in info for x in ('name', 'module', 'description', 'version'))
def install_deps(self):
for i in self.plugins.values():
self._install_deps(i)
@classmethod
def _install_deps(cls, info=None):
requirements = info.get('requirements', [])
if requirements:
pip_args = []
pip_args.append('install')
pip_args.append('--use-wheel')
for req in requirements:
pip_args.append(req)
logger.info('Installing requirements: ' + str(requirements))
pip.main(pip_args)
@classmethod
def _load_module(cls, name, root):
sys.path.append(root)
tmp = importlib.import_module(name)
sys.path.remove(root)
return tmp
@classmethod
def _load_plugin_from_info(cls, info, root):
if not cls.validate_info(info):
logger.warn('The module info is not valid.\n\t{}'.format(info))
return None, None
module = info["module"]
name = info["name"]
cls._install_deps(info)
tmp = cls._load_module(module, root)
candidate = None
for _, obj in inspect.getmembers(tmp):
if inspect.isclass(obj) and inspect.getmodule(obj) == tmp:
logger.debug(("Found plugin class:"
" {}@{}").format(obj, inspect.getmodule(obj)))
candidate = obj
break
if not candidate:
logger.debug("No valid plugin for: {}".format(module))
return
module = candidate(info=info)
return name, module
@classmethod
def _load_plugin(cls, root, filename):
fpath = os.path.join(root, filename)
logger.debug("Loading plugin: {}".format(fpath))
with open(fpath, 'r') as f:
info = yaml.load(f)
logger.debug("Info: {}".format(info))
return cls._load_plugin_from_info(info, root)
def _load_plugins(self):
plugins = {}
for search_folder in self._search_folders:
for root, dirnames, filenames in os.walk(search_folder):
for filename in fnmatch.filter(filenames, '*.senpy'):
name, plugin = self._load_plugin(root, filename)
if plugin and name:
plugins[name] = plugin
self._outdated = False
return plugins
def teardown(self, exception):
pass
@@ -312,12 +363,37 @@ class Senpy(object):
def plugins(self):
""" Return the plugins registered for a given application. """
if self._outdated:
self._plugin_list = plugins.load_plugins(self._search_folders)
self._outdated = False
self._plugin_list = self._load_plugins()
return self._plugin_list
def filter_plugins(self, **kwargs):
return plugins.pfilter(self.plugins, **kwargs)
""" Filter plugins by different criteria """
ptype = kwargs.pop('plugin_type', None)
logger.debug('#' * 100)
logger.debug('ptype {}'.format(ptype))
if ptype:
try:
ptype = ptype[0].upper() + ptype[1:]
pclass = getattr(plugins, ptype)
logger.debug('Class: {}'.format(pclass))
candidates = filter(lambda x: isinstance(x, pclass),
self.plugins.values())
except AttributeError:
raise Error('{} is not a valid type'.format(ptype))
else:
candidates = self.plugins.values()
logger.debug(candidates)
def matches(plug):
res = all(getattr(plug, k, None) == v for (k, v) in kwargs.items())
logger.debug(
"matching {} with {}: {}".format(plug.name, kwargs, res))
return res
if kwargs:
candidates = filter(matches, candidates)
return {p.name: p for p in candidates}
@property
def analysis_plugins(self):

View File

@@ -140,7 +140,7 @@ class SenpyMixin(object):
vp = item[kp]
temp[kp] = ser_or_down(vp)
return temp
elif isinstance(item, list) or isinstance(item, set):
elif isinstance(item, list):
return list(ser_or_down(i) for i in item)
else:
return item
@@ -181,10 +181,10 @@ class SenpyMixin(object):
obj = self
if hasattr(obj, "jsonld"):
obj = obj.jsonld()
self._validator.validate(obj)
jsonschema.validate(obj, self.schema)
def __str__(self):
return str(self.serialize())
return str(self.to_JSON())
class BaseModel(SenpyMixin, dict):
@@ -214,15 +214,15 @@ class BaseModel(SenpyMixin, dict):
temp['@type'] = getattr(self, '@type')
except AttributeError:
logger.warn('Creating an instance of an unknown model')
super(BaseModel, self).__init__(temp)
def _get_key(self, key):
if key is 'id':
key = '@id'
key = key.replace("__", ":", 1)
return key
def __setitem__(self, key, value):
dict.__setitem__(self, key, value)
def __delitem__(self, key):
dict.__delitem__(self, key)
@@ -236,49 +236,29 @@ class BaseModel(SenpyMixin, dict):
self.__setitem__(self._get_key(key), value)
def __delattr__(self, key):
try:
object.__delattr__(self, key)
except AttributeError:
self.__delitem__(self._get_key(key))
self.__delitem__(self._get_key(key))
def _plain_dict(self):
d = {k: v for (k, v) in self.items() if k[0] != "_"}
if 'id' in d:
d["@id"] = d.pop('id')
return d
_subtypes = {}
def register(rsubclass, rtype=None):
_subtypes[rtype or rsubclass.__name__] = rsubclass
_subtypes = {}
def from_dict(indict, cls=None):
if not cls:
target = indict.get('@type', None)
try:
if target and target in _subtypes:
cls = _subtypes[target]
else:
cls = BaseModel
except Exception:
cls = BaseModel
outdict = dict()
for k, v in indict.items():
if k == '@context':
pass
elif isinstance(v, dict):
v = from_dict(indict[k])
elif isinstance(v, list):
for ix, v2 in enumerate(v):
if isinstance(v2, dict):
v[ix] = from_dict(v2)
outdict[k] = v
return cls(**outdict)
def from_string(string, **kwargs):
return from_dict(json.loads(string), **kwargs)
def from_dict(indict):
target = indict.get('@type', None)
if target and target in _subtypes:
cls = _subtypes[target]
else:
cls = BaseModel
return cls(**indict)
def from_json(injson):
@@ -286,31 +266,15 @@ def from_json(injson):
return from_dict(indict)
def from_schema(name, schema=None, schema_file=None, base_classes=None):
def from_schema(name, schema_file=None, base_classes=None):
base_classes = base_classes or []
base_classes.append(BaseModel)
schema_file = schema_file or '{}.json'.format(name)
class_name = '{}{}'.format(name[0].upper(), name[1:])
if '/' not in 'schema_file':
schema_file = os.path.join(os.path.dirname(os.path.realpath(__file__)),
'schemas',
schema_file)
schema_path = 'file://' + schema_file
with open(schema_file) as f:
schema = json.load(f)
dct = {}
resolver = jsonschema.RefResolver(schema_path, schema)
dct['@type'] = name
dct['_schema_file'] = schema_file
dct['schema'] = schema
dct['_validator'] = jsonschema.Draft4Validator(schema, resolver=resolver)
newclass = type(class_name, tuple(base_classes), dct)
newclass = type(class_name, tuple(base_classes), {})
setattr(newclass, '@type', name)
setattr(newclass, 'schema', read_schema(schema_file))
setattr(newclass, 'class_name', class_name)
register(newclass, name)
return newclass
@@ -331,7 +295,6 @@ for i in [
'emotionPlugin',
'emotionSet',
'entry',
'help',
'plugin',
'plugins',
'response',
@@ -345,15 +308,12 @@ for i in [
_ErrorModel = from_schema('error')
class Error(SenpyMixin, Exception):
class Error(SenpyMixin, BaseException):
def __init__(self, message, *args, **kwargs):
super(Error, self).__init__(self, message, message)
self._error = _ErrorModel(message=message, *args, **kwargs)
self.message = message
def validate(self, obj=None):
self._error.validate()
def __getitem__(self, key):
return self._error[key]
@@ -377,8 +337,5 @@ class Error(SenpyMixin, Exception):
def __delattr__(self, key):
delattr(self._error, key)
def __str__(self):
return str(self.to_JSON(with_context=False))
register(Error, 'error')

View File

@@ -1,28 +1,19 @@
from future import standard_library
standard_library.install_aliases()
import inspect
import os.path
import os
import pickle
import logging
import tempfile
import copy
import fnmatch
import inspect
import sys
import subprocess
import importlib
import yaml
import threading
from .. import models, utils
from ..api import API_PARAMS
from .. import models
logger = logging.getLogger(__name__)
class Plugin(models.Plugin):
class SenpyPlugin(models.Plugin):
def __init__(self, info=None):
"""
Provides a canonical name for plugins and serves as base for other
@@ -33,9 +24,8 @@ class Plugin(models.Plugin):
"information for the plugin."))
logger.debug("Initialising {}".format(info))
id = 'plugins/{}_{}'.format(info['name'], info['version'])
super(Plugin, self).__init__(id=id, **info)
super(SenpyPlugin, self).__init__(id=id, **info)
self.is_activated = False
self._lock = threading.Lock()
def get_folder(self):
return os.path.dirname(inspect.getfile(self.__class__))
@@ -46,26 +36,8 @@ class Plugin(models.Plugin):
def deactivate(self):
pass
def test(self):
if not hasattr(self, 'test_cases'):
import inspect
raise AttributeError(('Plugin {} [{}] does not have any defined '
'test cases').format(self.id, inspect.getfile(self.__class__)))
for case in self.test_cases:
res = list(self.analyse_entry(models.Entry(case['entry']),
case['params']))
exp = case['expected']
if not isinstance(exp, list):
exp = [exp]
utils.check_template(res, exp)
for r in res:
r.validate()
SenpyPlugin = Plugin
class AnalysisPlugin(Plugin):
class AnalysisPlugin(SenpyPlugin):
def analyse(self, *args, **kwargs):
raise NotImplemented(
@@ -78,21 +50,15 @@ class AnalysisPlugin(Plugin):
Note that this method may yield an annotated entry or a list of
entries (e.g. in a tokenizer)
"""
text = entry['nif:isString']
text = entry['text']
params = copy.copy(parameters)
params['input'] = text
results = self.analyse(**params)
for i in results.entries:
yield i
def analyse_entries(self, entries, parameters):
for entry in entries:
logger.debug('Analysing entry with plugin {}: {}'.format(self, entry))
for result in self.analyse_entry(entry, parameters):
yield result
class ConversionPlugin(Plugin):
class ConversionPlugin(SenpyPlugin):
pass
@@ -120,12 +86,7 @@ class ShelfMixin(object):
if not hasattr(self, '_sh') or self._sh is None:
self.__dict__['_sh'] = {}
if os.path.isfile(self.shelf_file):
try:
self.__dict__['_sh'] = pickle.load(open(self.shelf_file, 'rb'))
except (IndexError, EOFError, pickle.UnpicklingError):
logger.warning('{} has a corrupted shelf file!'.format(self.id))
if not self.get('force_shelf', False):
raise
self.__dict__['_sh'] = pickle.load(open(self.shelf_file, 'rb'))
return self._sh
@sh.deleter
@@ -147,137 +108,3 @@ class ShelfMixin(object):
if hasattr(self, '_sh') and self._sh is not None:
with open(self.shelf_file, 'wb') as f:
pickle.dump(self._sh, f)
default_plugin_type = API_PARAMS['plugin_type']['default']
def pfilter(plugins, **kwargs):
""" Filter plugins by different criteria """
if isinstance(plugins, models.Plugins):
plugins = plugins.plugins
elif isinstance(plugins, dict):
plugins = plugins.values()
ptype = kwargs.pop('plugin_type', default_plugin_type)
logger.debug('#' * 100)
logger.debug('ptype {}'.format(ptype))
if ptype:
try:
ptype = ptype[0].upper() + ptype[1:]
pclass = globals()[ptype]
logger.debug('Class: {}'.format(pclass))
candidates = filter(lambda x: isinstance(x, pclass),
plugins)
except KeyError:
raise models.Error('{} is not a valid type'.format(ptype))
else:
candidates = plugins
logger.debug(candidates)
def matches(plug):
res = all(getattr(plug, k, None) == v for (k, v) in kwargs.items())
logger.debug(
"matching {} with {}: {}".format(plug.name, kwargs, res))
return res
if kwargs:
candidates = filter(matches, candidates)
return {p.name: p for p in candidates}
def validate_info(info):
return all(x in info for x in ('name', 'module', 'description', 'version'))
def load_module(name, root=None):
if root:
sys.path.append(root)
tmp = importlib.import_module(name)
if root:
sys.path.remove(root)
return tmp
def log_subprocess_output(process):
for line in iter(process.stdout.readline, b''):
logger.info('%r', line)
for line in iter(process.stderr.readline, b''):
logger.error('%r', line)
def install_deps(*plugins):
for info in plugins:
requirements = info.get('requirements', [])
if requirements:
pip_args = ['pip']
pip_args.append('install')
pip_args.append('--use-wheel')
for req in requirements:
pip_args.append(req)
logger.info('Installing requirements: ' + str(requirements))
process = subprocess.Popen(pip_args,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
log_subprocess_output(process)
exitcode = process.wait()
if exitcode != 0:
raise models.Error("Dependencies not properly installed")
def load_plugin_from_info(info, root=None, validator=validate_info, install=True):
if not root and '_path' in info:
root = os.path.dirname(info['_path'])
if not validator(info):
raise ValueError('Plugin info is not valid: {}'.format(info))
module = info["module"]
try:
tmp = load_module(module, root)
except ImportError:
if not install:
raise
install_deps(info)
tmp = load_module(module, root)
candidate = None
for _, obj in inspect.getmembers(tmp):
if inspect.isclass(obj) and inspect.getmodule(obj) == tmp:
logger.debug(("Found plugin class:"
" {}@{}").format(obj, inspect.getmodule(obj)))
candidate = obj
break
if not candidate:
logger.debug("No valid plugin for: {}".format(module))
return
module = candidate(info=info)
return module
def parse_plugin_info(fpath):
logger.debug("Loading plugin: {}".format(fpath))
with open(fpath, 'r') as f:
info = yaml.load(f)
info['_path'] = fpath
name = info['name']
return name, info
def load_plugin(fpath):
name, info = parse_plugin_info(fpath)
logger.debug("Info: {}".format(info))
plugin = load_plugin_from_info(info)
return name, plugin
def load_plugins(folders, loader=load_plugin):
plugins = {}
for search_folder in folders:
for root, dirnames, filenames in os.walk(search_folder):
# Do not look for plugins in hidden or special folders
dirnames[:] = [d for d in dirnames if d[0] not in ['.', '_']]
for filename in fnmatch.filter(filenames, '*.senpy'):
fpath = os.path.join(root, filename)
name, plugin = loader(fpath)
if plugin and name:
plugins[name] = plugin
return plugins

View File

@@ -0,0 +1,52 @@
from senpy.plugins import EmotionConversionPlugin
from senpy.models import EmotionSet, Emotion, Error
import logging
logger = logging.getLogger(__name__)
class CentroidConversion(EmotionConversionPlugin):
def _forward_conversion(self, original):
"""Sum the VAD value of all categories found."""
res = Emotion()
for e in original.onyx__hasEmotion:
category = e.onyx__hasEmotionCategory
if category in self.centroids:
for dim, value in self.centroids[category].items():
try:
res[dim] += value
except Exception:
res[dim] = value
return res
def _backwards_conversion(self, original):
"""Find the closest category"""
dimensions = list(self.centroids.values())[0]
def distance(e1, e2):
return sum((e1[k] - e2.get(self.aliases[k], 0)) for k in dimensions)
emotion = ''
mindistance = 10000000000000000000000.0
for state in self.centroids:
d = distance(self.centroids[state], original)
if d < mindistance:
mindistance = d
emotion = state
result = Emotion(onyx__hasEmotionCategory=emotion)
return result
def convert(self, emotionSet, fromModel, toModel, params):
cf, ct = self.centroids_direction
logger.debug('{}\n{}\n{}\n{}'.format(emotionSet, fromModel, toModel, params))
e = EmotionSet()
if fromModel == cf:
e.onyx__hasEmotion.append(self._forward_conversion(emotionSet))
elif fromModel == ct:
for i in emotionSet.onyx__hasEmotion:
e.onyx__hasEmotion.append(self._backwards_conversion(i))
else:
raise Error('EMOTION MODEL NOT KNOWN')
yield e

View File

@@ -1,153 +0,0 @@
from senpy.plugins import EmotionConversionPlugin
from senpy.models import EmotionSet, Emotion, Error
import logging
logger = logging.getLogger(__name__)
class CentroidConversion(EmotionConversionPlugin):
def __init__(self, info):
if 'centroids' not in info:
raise Error('Centroid conversion plugins should provide '
'the centroids in their senpy file')
if 'onyx:doesConversion' not in info:
if 'centroids_direction' not in info:
raise Error('Please, provide centroids direction')
cf, ct = info['centroids_direction']
info['onyx:doesConversion'] = [{
'onyx:conversionFrom': cf,
'onyx:conversionTo': ct
}, {
'onyx:conversionFrom': ct,
'onyx:conversionTo': cf
}]
if 'aliases' in info:
aliases = info['aliases']
ncentroids = {}
for k1, v1 in info['centroids'].items():
nv1 = {}
for k2, v2 in v1.items():
nv1[aliases.get(k2, k2)] = v2
ncentroids[aliases.get(k1, k1)] = nv1
info['centroids'] = ncentroids
super(CentroidConversion, self).__init__(info)
self.dimensions = set()
for c in self.centroids.values():
self.dimensions.update(c.keys())
self.neutralPoints = self.get("neutralPoints", dict())
if not self.neutralPoints:
for i in self.dimensions:
self.neutralPoints[i] = self.get("neutralValue", 0)
def _forward_conversion(self, original):
"""Sum the VAD value of all categories found weighted by intensity.
Intensities are scaled by onyx:maxIntensityValue if it is present, else maxIntensityValue
is assumed to be one. Emotion entries that do not have onxy:hasEmotionIntensity specified
are assumed to have maxIntensityValue. Emotion entries that do not have
onyx:hasEmotionCategory specified are ignored."""
res = Emotion()
maxIntensity = float(original.get("onyx:maxIntensityValue", 1))
for e in original.onyx__hasEmotion:
category = e.get("onyx:hasEmotionCategory", None)
if not category:
continue
intensity = e.get("onyx:hasEmotionIntensity", maxIntensity) / maxIntensity
if not intensity:
continue
centroid = self.centroids.get(category, None)
if centroid:
for dim, value in centroid.items():
neutral = self.neutralPoints[dim]
if dim not in res:
res[dim] = 0
res[dim] += (value - neutral) * intensity + neutral
return res
def _backwards_conversion(self, original):
"""Find the closest category"""
centroids = self.centroids
neutralPoints = self.neutralPoints
dimensions = self.dimensions
def distance_k(centroid, original, k):
# k component of the distance between the value and a given centroid
return (centroid.get(k, neutralPoints[k]) - original.get(k, neutralPoints[k]))**2
def distance(centroid):
return sum(distance_k(centroid, original, k) for k in dimensions)
emotion = min(centroids, key=lambda x: distance(centroids[x]))
result = Emotion(onyx__hasEmotionCategory=emotion)
result.onyx__algorithmConfidence = distance(centroids[emotion])
return result
def convert(self, emotionSet, fromModel, toModel, params):
cf, ct = self.centroids_direction
logger.debug(
'{}\n{}\n{}\n{}'.format(emotionSet, fromModel, toModel, params))
e = EmotionSet()
if fromModel == cf and toModel == ct:
e.onyx__hasEmotion.append(self._forward_conversion(emotionSet))
elif fromModel == ct and toModel == cf:
for i in emotionSet.onyx__hasEmotion:
e.onyx__hasEmotion.append(self._backwards_conversion(i))
else:
raise Error('EMOTION MODEL NOT KNOWN')
yield e
def test(self, info=None):
if not info:
info = {
"name": "CentroidTest",
"description": "Centroid test",
"version": 0,
"centroids": {
"c1": {"V1": 0.5,
"V2": 0.5},
"c2": {"V1": -0.5,
"V2": 0.5},
"c3": {"V1": -0.5,
"V2": -0.5},
"c4": {"V1": 0.5,
"V2": -0.5}},
"aliases": {
"V1": "X-dimension",
"V2": "Y-dimension"
},
"centroids_direction": ["emoml:big6", "emoml:fsre-dimensions"]
}
c = CentroidConversion(info)
es1 = EmotionSet()
e1 = Emotion()
e1.onyx__hasEmotionCategory = "c1"
es1.onyx__hasEmotion.append(e1)
res = c._forward_conversion(es1)
assert res["X-dimension"] == 0.5
assert res["Y-dimension"] == 0.5
e2 = Emotion()
e2.onyx__hasEmotionCategory = "c2"
es1.onyx__hasEmotion.append(e2)
res = c._forward_conversion(es1)
assert res["X-dimension"] == 0
assert res["Y-dimension"] == 1
e = Emotion()
e["X-dimension"] = -0.2
e["Y-dimension"] = -0.3
res = c._backwards_conversion(e)
assert res["onyx:hasEmotionCategory"] == "c3"
e = Emotion()
e["X-dimension"] = -0.2
e["Y-dimension"] = 0.3
res = c._backwards_conversion(e)
assert res["onyx:hasEmotionCategory"] == "c2"

View File

@@ -1,52 +0,0 @@
---
name: Ekman2FSRE
module: senpy.plugins.conversion.emotion.centroids
description: Plugin to convert emotion sets from Ekman to VAD
version: 0.2
# No need to specify onyx:doesConversion because centroids.py adds it automatically from centroids_direction
neutralValue: 5.0
centroids:
anger:
A: 6.95
D: 5.1
V: 2.7
S: 5.0
disgust:
A: 5.3
D: 8.05
V: 2.7
S: 5.0
fear:
A: 6.5
D: 3.6
V: 3.2
S: 5.0
happiness:
A: 7.22
D: 6.28
V: 8.6
S: 5.0
sadness:
A: 5.21
D: 2.82
V: 2.21
S: 5.0
surprise:
A: 5.0
D: 5.0
V: 5.0
S: 10.0
centroids_direction:
- emoml:big6
- emoml:fsre-dimensions
aliases: # These are aliases for any key in the centroid, to avoid repeating a long name several times
A: emoml:fsre-dimensions_arousal
V: emoml:fsre-dimensions_valence
D: emoml:fsre-dimensions_potency
S: emoml:fsre-dimensions_unpredictability
anger: emoml:big6anger
disgust: emoml:big6disgust
fear: emoml:big6fear
happiness: emoml:big6happiness
sadness: emoml:big6sadness
surprise: emoml:big6surprise

View File

@@ -1,40 +1,38 @@
---
name: Ekman2PAD
module: senpy.plugins.conversion.emotion.centroids
name: Ekman2VAD
module: senpy.plugins.conversion.centroids
description: Plugin to convert emotion sets from Ekman to VAD
version: 0.2
# No need to specify onyx:doesConversion because centroids.py adds it automatically from centroids_direction
neutralValue: 5.0
version: 0.1
onyx:doesConversion:
- onyx:conversionFrom: emoml:big6
onyx:conversionTo: emoml:fsre-dimensions
- onyx:conversionFrom: emoml:fsre-dimensions
onyx:conversionTo: emoml:big6
centroids:
anger:
emoml:big6anger:
A: 6.95
D: 5.1
V: 2.7
disgust:
emoml:big6disgust:
A: 5.3
D: 8.05
V: 2.7
fear:
emoml:big6fear:
A: 6.5
D: 3.6
V: 3.2
happiness:
emoml:big6happiness:
A: 7.22
D: 6.28
V: 8.6
sadness:
emoml:big6sadness:
A: 5.21
D: 2.82
V: 2.21
centroids_direction:
- emoml:big6
- emoml:pad
aliases: # These are aliases for any key in the centroid, to avoid repeating a long name several times
A: emoml:pad-dimensions:arousal
V: emoml:pad-dimensions:pleasure
D: emoml:pad-dimensions:dominance
anger: emoml:big6anger
disgust: emoml:big6disgust
fear: emoml:big6fear
happiness: emoml:big6happiness
sadness: emoml:big6sadness
- emoml:fsre-dimensions
aliases:
A: emoml:arousal
V: emoml:valence
D: emoml:dominance

View File

@@ -1,7 +1,7 @@
import random
from senpy.plugins import EmotionPlugin
from senpy.models import EmotionSet, Emotion, Entry
from senpy.models import EmotionSet, Emotion
class RmoRandPlugin(EmotionPlugin):
@@ -16,11 +16,3 @@ class RmoRandPlugin(EmotionPlugin):
emotionSet.prov__wasGeneratedBy = self.id
entry.emotions.append(emotionSet)
yield entry
def test(self):
params = dict()
results = list()
for i in range(100):
res = next(self.analyse_entry(Entry(nif__isString="Hello"), params))
res.validate()
results.append(res.emotions[0]['onyx:hasEmotion'][0]['onyx:hasEmotionCategory'])

View File

@@ -1,7 +1,7 @@
import random
from senpy.plugins import SentimentPlugin
from senpy.models import Sentiment, Entry
from senpy.models import Sentiment
class RandPlugin(SentimentPlugin):
@@ -22,13 +22,3 @@ class RandPlugin(SentimentPlugin):
entry.sentiments.append(sentiment)
entry.language = lang
yield entry
def test(self):
params = dict()
results = list()
for i in range(100):
res = next(self.analyse_entry(Entry(nif__isString="Hello"), params))
res.validate()
results.append(res.sentiments[0]['marl:hasPolarity'])
assert 'marl:Positive' in results
assert 'marl:Negative' in results

View File

@@ -1,64 +0,0 @@
from senpy.plugins import AnalysisPlugin
from senpy.models import Entry
from nltk.tokenize.punkt import PunktSentenceTokenizer
from nltk.tokenize.simple import LineTokenizer
import nltk
class SplitPlugin(AnalysisPlugin):
def activate(self):
nltk.download('punkt')
def analyse_entry(self, entry, params):
chunker_type = params.get("delimiter", "sentence")
original_text = entry.get('nif:isString', None)
if chunker_type == "sentence":
tokenizer = PunktSentenceTokenizer()
if chunker_type == "paragraph":
tokenizer = LineTokenizer()
chars = tokenizer.span_tokenize(original_text)
for i, chunk in enumerate(tokenizer.tokenize(original_text)):
e = Entry()
e['nif:isString'] = chunk
if entry.id:
e.id = entry.id + "#char={},{}".format(chars[i][0], chars[i][1])
yield e
test_cases = [
{
'entry': {
'nif:isString': 'Hello. World.'
},
'params': {
'delimiter': 'sentence',
},
'expected': [
{
'nif:isString': 'Hello.'
},
{
'nif:isString': 'World.'
}
]
},
{
'entry': {
"id": ":test",
'nif:isString': 'Hello. World.'
},
'params': {
'delimiter': 'sentence',
},
'expected': [
{
"@id": ":test#char=0,6",
'nif:isString': 'Hello.'
},
{
"@id": ":test#char=7,13",
'nif:isString': 'World.'
}
]
}
]

View File

@@ -1,19 +0,0 @@
---
name: split
module: senpy.plugins.misc.split
description: A sample plugin that chunks input text
author: "@militarpancho"
version: '0.2'
url: "https://github.com/gsi-upm/senpy"
requirements:
- nltk
extra_params:
delimiter:
aliases:
- type
- t
required: false
default: sentence
options:
- sentence
- paragraph

View File

@@ -12,7 +12,7 @@ class Sentiment140Plugin(SentimentPlugin):
json.dumps({
"language": lang,
"data": [{
"text": entry['nif:isString']
"text": entry.text
}]
}))
p = params.get("prefix", None)
@@ -34,20 +34,3 @@ class Sentiment140Plugin(SentimentPlugin):
entry.sentiments.append(sentiment)
entry.language = lang
yield entry
test_cases = [
{
'entry': {
'nif:isString': 'I love Titanic'
},
'params': {},
'expected': {
"nif:isString": "I love Titanic",
'sentiments': [
{
'marl:hasPolarity': 'marl:Positive',
}
]
}
}
]

View File

@@ -20,16 +20,10 @@
"@id": "me:hasSuggestions",
"@container": "@set"
},
"onyx:hasEmotion": {
"@container": "@set"
},
"emotions": {
"@id": "onyx:hasEmotionSet",
"@container": "@set"
},
"onyx:hasEmotion": {
"@container": "@set"
},
"sentiments": {
"@id": "marl:hasOpinion",
"@container": "@set"
@@ -43,12 +37,6 @@
"@type": "@id",
"@container": "@set"
},
"options": {
"@container": "@set"
},
"plugins": {
"@container": "@set"
},
"prov:wasGeneratedBy": {
"@type": "@id"
},

View File

@@ -5,7 +5,7 @@
"nif:beginIndex": {"type": "integer"},
"nif:endIndex": {"type": "integer"},
"nif:anchorOf": {
"description": "Piece of context that contains the Emotion",
"description": "Piece of context that contains the Sentiment",
"type": "string"
},
"onyx:hasDimension": {

View File

@@ -6,7 +6,7 @@
"type": "string"
},
"nif:isString": {
"description": "String contained in this Context. Alternative: nif:isString",
"description": "String contained in this Context",
"type": "string"
},
"sentiments": {

View File

@@ -1,17 +0,0 @@
{
"$schema": "http://json-schema.org/draft-04/schema#",
"allOf": [
{"$ref": "response.json"},
{
"title": "Help",
"description": "Help containing accepted parameters",
"type": "object",
"properties": {
"parameters": {
"type": "object"
}
},
"required": "parameters"
}
]
}

View File

@@ -3,14 +3,14 @@
"allOf": [
{"$ref": "response.json"},
{
"required": ["plugins"],
"properties": {
"plugins": {
"type": "array",
"default": [],
"items": {
"$ref": "plugin.json"
}
},
"@type": {
}
}
}

View File

@@ -2,12 +2,7 @@
"$schema": "http://json-schema.org/draft-04/schema#",
"type": "object",
"properties": {
"@type": {"type": "string"},
"parameters": {
"type": "object",
"default": {}
}
"@type": {"type": "string"}
},
"required": ["@type"]

View File

@@ -18,16 +18,10 @@
"type": "string"
},
"analysis": {
"default": [],
"type": "array",
"default": [],
"items": {
"anyOf": [
{
"$ref": "analysis.json"
},{
"type": "string"
}
]
"$ref": "analysis.json"
}
},
"entries": {

View File

@@ -1,7 +1,7 @@
var ONYX = "http://www.gsi.dit.upm.es/ontologies/onyx/ns#";
var RDF_TYPE = "http://www.w3.org/1999/02/22-rdf-syntax-ns#type";
var plugins_params={};
var default_params = JSON.parse($.ajax({type: "GET", url: "/api?help=True" , async: false}).responseText);
function replaceURLWithHTMLLinks(text) {
console.log('Text: ' + text);
var exp = /(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/ig;
@@ -28,68 +28,54 @@ function hashchanged(){
$(document).ready(function() {
var response = JSON.parse($.ajax({type: "GET", url: "/api/plugins/" , async: false}).responseText);
var defaultPlugin= JSON.parse($.ajax({type: "GET", url: "/api/plugins/default" , async: false}).responseText);
html="";
html="";
var availablePlugins = document.getElementById('availablePlugins');
plugins = response.plugins;
gplugins = {};
for (r in plugins){
ptype = plugins[r]['@type'];
if(gplugins[ptype] == undefined){
gplugins[ptype] = [r]
}else{
gplugins[ptype].push(r)
}
}
for (g in gplugins){
html += "<optgroup label=\""+g+"\">"
for (r in gplugins[g]){
plugin = plugins[r]
if (plugin["name"]){
if (plugin["name"] == defaultPlugin["name"]){
if (plugin["is_activated"]){
html+= "<option value=\""+plugin["name"]+"\" selected=\"selected\">"+plugin["name"]+"</option>"
}else{
html+= "<option value=\""+plugin["name"]+"\" selected=\"selected\" disabled=\"disabled\">"+plugin["name"]+"</option>"
}
}
else{
if (plugin["is_activated"]){
html+= "<option value=\""+plugin["name"]+"\">"+plugin["name"]+"</option>"
}
else{
html+= "<option value=\""+plugin["name"]+"\" disabled=\"disabled\">"+plugin["name"]+"</option>"
}
}
}
for (r in plugins){
plugin = plugins[r]
if (plugin["name"]){
if (plugin["name"] == defaultPlugin["name"]){
if (plugin["is_activated"]){
html+= "<option value=\""+plugin["name"]+"\" selected=\"selected\">"+plugin["name"]+"</option>"
}else{
html+= "<option value=\""+plugin["name"]+"\" selected=\"selected\" disabled=\"disabled\">"+plugin["name"]+"</option>"
}
}
else{
if (plugin["is_activated"]){
html+= "<option value=\""+plugin["name"]+"\">"+plugin["name"]+"</option>"
}
else{
html+= "<option value=\""+plugin["name"]+"\" disabled=\"disabled\">"+plugin["name"]+"</option>"
}
}
}
if (plugin["extra_params"]){
plugins_params[plugin["name"]]={};
for (param in plugin["extra_params"]){
if (typeof plugin["extra_params"][param] !="string"){
var params = new Array();
var alias = plugin["extra_params"][param]["aliases"][0];
params[alias]=new Array();
for (option in plugin["extra_params"][param]["options"]){
params[alias].push(plugin["extra_params"][param]["options"][option])
}
plugins_params[plugin["name"]][alias] = (params[alias])
}
}
}
var pluginList = document.createElement('li');
if (plugin["extra_params"]){
plugins_params[plugin["name"]]={};
for (param in plugin["extra_params"]){
if (typeof plugin["extra_params"][param] !="string"){
var params = new Array();
var alias = plugin["extra_params"][param]["aliases"][0];
params[alias]=new Array();
for (option in plugin["extra_params"][param]["options"]){
params[alias].push(plugin["extra_params"][param]["options"][option])
}
plugins_params[plugin["name"]][alias] = (params[alias])
}
}
}
var pluginList = document.createElement('li');
newHtml = ""
if(plugin.url) {
newHtml= "<a href="+plugin.url+">" + plugin.name + "</a>";
}else {
newHtml= plugin["name"];
}
newHtml += ": " + replaceURLWithHTMLLinks(plugin.description);
pluginList.innerHTML = newHtml;
availablePlugins.appendChild(pluginList)
}
html += "</optgroup>"
}
newHtml = ""
if(plugin.url) {
newHtml= "<a href="+plugin.url+">" + plugin.name + "</a>";
}else {
newHtml= plugin["name"];
}
newHtml += ": " + replaceURLWithHTMLLinks(plugin.description);
pluginList.innerHTML = newHtml;
availablePlugins.appendChild(pluginList)
}
document.getElementById('plugins').innerHTML = html;
change_params();
@@ -102,23 +88,8 @@ $(document).ready(function() {
function change_params(){
var plugin = document.getElementById("plugins").options[document.getElementById("plugins").selectedIndex].value;
html=""
for (param in default_params){
if ((default_params[param]['options']) && (['help','conversion'].indexOf(param) < 0)){
html+= "<label> "+param+"</label>"
html+= "<select id=\""+param+"\" name=\""+param+"\">"
for (option in default_params[param]['options']){
if (default_params[param]['options'][option] == default_params[param]['default']){
html+="<option value \""+default_params[param]['options'][option]+"\" selected >"+default_params[param]['options'][option]+"</option>"
}
else{
html+="<option value \""+default_params[param]['options'][option]+"\">"+default_params[param]['options'][option]+"</option>"
}
}
html+="</select><br>"
}
}
html=""
for (param in plugins_params[plugin]){
if (param || plugins_params[plugin][param].length > 1){
html+= "<label> Parameter "+param+"</label>"
@@ -149,32 +120,15 @@ function load_JSON(){
}
}
}
for (param in default_params){
if ((param != null) && (default_params[param]['options']) && (['help','conversion'].indexOf(param) < 0)){
var param_value = encodeURIComponent(document.getElementById(param).options[document.getElementById(param).selectedIndex].text);
if (param_value){
url+="&"+param+"="+param_value
}
}
}
var response = $.ajax({type: "GET", url: url , async: false}).responseText;
rawcontainer.innerHTML = replaceURLWithHTMLLinks(response)
document.getElementById("input_request").innerHTML = "<a href='"+url+"'>"+url+"</a>"
document.getElementById("results-div").style.display = 'block';
try {
response = JSON.parse(response);
var response = JSON.parse($.ajax({type: "GET", url: url , async: false}).responseText);
var options = {
mode: 'view'
};
var editor = new JSONEditor(container, options, response);
editor.expandAll();
}
catch(err){
console.log("Error decoding JSON (got turtle?)");
}
rawcontainer.innerHTML = replaceURLWithHTMLLinks(JSON.stringify(response, undefined, 2))
document.getElementById("input_request").innerHTML = "<a href='"+url+"'>"+url+"</a>"
document.getElementById("results-div").style.display = 'block';
}

View File

@@ -47,7 +47,7 @@
This website is the senpy Playground, which allows you to test the instance of senpy in this server. It provides a user-friendly interface to the functions exposed by the senpy API.
</p>
<p>
Once you get comfortable with the parameters and results, you are encouraged to issue your own requests to the API endpoint. You can find examples of API URL's when you try out a plugin with the "Analyse!" button on the "Test it" tab.
Once you get comfortable with the parameters and results, you are encouraged to issue your own requests to the API endpoint, which should be <a href="/api">here</a>.
</p>
<p>
These are some of the things you can do with the API:

View File

@@ -1,25 +0,0 @@
from . import models
def check_template(indict, template):
if isinstance(template, dict) and isinstance(indict, dict):
for k, v in template.items():
if k not in indict:
return '{} not in {}'.format(k, indict)
check_template(indict[k], v)
elif isinstance(template, list) and isinstance(indict, list):
if len(indict) != len(template):
raise models.Error('Different size for {} and {}'.format(indict, template))
for e in template:
found = False
for i in indict:
try:
check_template(i, e)
found = True
except models.Error as ex:
continue
if not found:
raise models.Error('{} not found in {}'.format(e, indict))
else:
if indict != template:
raise models.Error('{} and {} are different'.format(indict, template))

View File

@@ -11,7 +11,7 @@ def read_version(versionfile=DEFAULT_FILE):
try:
with open(versionfile) as f:
return f.read().strip()
except IOError: # pragma: no cover
except IOError:
logger.error('Running an unknown version of senpy. Be careful!.')
return '0.0'

View File

@@ -12,6 +12,3 @@ max-line-length = 100
universal=1
[tool:pytest]
addopts = --cov=senpy --cov-report term-missing
[coverage:report]
omit = senpy/__main__.py

View File

@@ -1,26 +0,0 @@
from senpy.plugins import AnalysisPlugin
import multiprocessing
def _train(process_number):
return process_number
class AsyncPlugin(AnalysisPlugin):
def _do_async(self, num_processes):
pool = multiprocessing.Pool(processes=num_processes)
values = pool.map(_train, range(num_processes))
return values
def activate(self):
self.value = self._do_async(4)
def analyse_entry(self, entry, params):
values = self._do_async(2)
entry.async_values = values
yield entry
def test(self):
pass

View File

@@ -1,8 +0,0 @@
---
name: Async
module: asyncplugin
description: I am async
author: "@balkian"
version: '0.1'
async: true
extra_params: {}

View File

@@ -3,9 +3,5 @@ from senpy.plugins import SentimentPlugin
class DummyPlugin(SentimentPlugin):
def analyse_entry(self, entry, params):
entry['nif:iString'] = entry['nif:isString'][::-1]
entry.reversed = entry.get('reversed', 0) + 1
entry.text = entry.text[::-1]
yield entry
def test(self):
pass

View File

@@ -1,14 +1,11 @@
from senpy.plugins import AnalysisPlugin
from senpy.plugins import SenpyPlugin
from time import sleep
class SleepPlugin(AnalysisPlugin):
class SleepPlugin(SenpyPlugin):
def activate(self, *args, **kwargs):
sleep(self.timeout)
def analyse_entry(self, entry, params):
sleep(float(params.get("timeout", self.timeout)))
yield entry
def test(self):
pass

View File

@@ -4,7 +4,7 @@
"description": "I am dummy",
"author": "@balkian",
"version": "0.1",
"timeout": 0.05,
"timeout": 0.5,
"extra_params": {
"timeout": {
"@id": "timeout_sleep",

View File

@@ -11,24 +11,24 @@ class APITest(TestCase):
def test_api_params(self):
"""The API should not define any required parameters without a default"""
parse_params({}, API_PARAMS)
parse_params({}, spec=API_PARAMS)
def test_web_params(self):
"""The WEB should not define any required parameters without a default"""
parse_params({}, WEB_PARAMS)
parse_params({}, spec=WEB_PARAMS)
def test_basic(self):
a = {}
try:
parse_params(a, NIF_PARAMS)
parse_params(a, spec=NIF_PARAMS)
raise AssertionError()
except Error:
pass
a = {'input': 'hello'}
p = parse_params(a, NIF_PARAMS)
p = parse_params(a, spec=NIF_PARAMS)
assert 'input' in p
b = {'i': 'hello'}
p = parse_params(b, NIF_PARAMS)
p = parse_params(b, spec=NIF_PARAMS)
assert 'input' in p
def test_plugin(self):
@@ -40,18 +40,18 @@ class APITest(TestCase):
}
}
try:
parse_params(query, plug_params)
parse_params(query, spec=plug_params)
raise AssertionError()
except Error:
pass
query['hello'] = 'world'
p = parse_params(query, plug_params)
p = parse_params(query, spec=plug_params)
assert 'hello' in p
assert p['hello'] == 'world'
del query['hello']
query['hiya'] = 'dlrow'
p = parse_params(query, plug_params)
p = parse_params(query, spec=plug_params)
assert 'hello' in p
assert 'hiya' in p
assert p['hello'] == 'dlrow'
@@ -63,17 +63,6 @@ class APITest(TestCase):
'default': 1
}
}
p = parse_params({}, spec)
p = parse_params({}, spec=spec)
assert 'hello' in p
assert p['hello'] == 1
def test_call(self):
call = {
'input': "Aloha my friend",
'algo': "Dummy"
}
p = parse_params(call, API_PARAMS, NIF_PARAMS)
assert 'algorithm' in p
assert "Dummy" in p['algorithm']
assert 'input' in p
assert p['input'] == 'Aloha my friend'

View File

@@ -17,19 +17,16 @@ def parse_resp(resp):
class BlueprintsTest(TestCase):
@classmethod
def setUpClass(cls):
"""Set up only once, and re-use in every individual test"""
cls.app = Flask("test_extensions")
cls.app.debug = False
cls.client = cls.app.test_client()
cls.senpy = Senpy()
cls.senpy.init_app(cls.app)
cls.dir = os.path.join(os.path.dirname(__file__), "..")
cls.senpy.add_folder(cls.dir)
cls.senpy.activate_plugin("Dummy", sync=True)
cls.senpy.activate_plugin("DummyRequired", sync=True)
cls.senpy.default_plugin = 'Dummy'
def setUp(self):
self.app = Flask("test_extensions")
self.client = self.app.test_client()
self.senpy = Senpy()
self.senpy.init_app(self.app)
self.dir = os.path.join(os.path.dirname(__file__), "..")
self.senpy.add_folder(self.dir)
self.senpy.activate_plugin("Dummy", sync=True)
self.senpy.activate_plugin("DummyRequired", sync=True)
self.senpy.default_plugin = 'Dummy'
def assertCode(self, resp, code):
self.assertEqual(resp.status_code, code)
@@ -38,7 +35,6 @@ class BlueprintsTest(TestCase):
"""
Calling with no arguments should ask the user for more arguments
"""
self.app.debug = False
resp = self.client.get("/api/")
self.assertCode(resp, 400)
js = parse_resp(resp)
@@ -55,7 +51,7 @@ class BlueprintsTest(TestCase):
The dummy plugin returns an empty response,\
it should contain the context
"""
resp = self.client.get("/api/?i=My aloha mohame&with_parameters=True")
resp = self.client.get("/api/?i=My aloha mohame")
self.assertCode(resp, 200)
js = parse_resp(resp)
logging.debug("Got response: %s", js)
@@ -66,7 +62,7 @@ class BlueprintsTest(TestCase):
"""
Extra params that have a default should
"""
resp = self.client.get("/api/?i=My aloha mohame&algo=Dummy&with_parameters=true")
resp = self.client.get("/api/?i=My aloha mohame&algo=Dummy")
self.assertCode(resp, 200)
js = parse_resp(resp)
logging.debug("Got response: %s", js)
@@ -78,7 +74,6 @@ class BlueprintsTest(TestCase):
Extra params that have a required argument that does not
have a default should raise an error.
"""
self.app.debug = False
resp = self.client.get("/api/?i=My aloha mohame&algo=DummyRequired")
self.assertCode(resp, 400)
js = parse_resp(resp)
@@ -90,7 +85,6 @@ class BlueprintsTest(TestCase):
The dummy plugin returns an empty response,\
it should contain the context
"""
self.app.debug = False
resp = self.client.get("/api/?i=My aloha mohame&algo=DOESNOTEXIST")
self.assertCode(resp, 404)
js = parse_resp(resp)
@@ -157,10 +151,3 @@ class BlueprintsTest(TestCase):
self.assertCode(resp, 200)
js = parse_resp(resp)
assert "$schema" in js
def test_help(self):
resp = self.client.get("/api/?help=true")
self.assertCode(resp, 200)
js = parse_resp(resp)
assert "parameters" in js
assert "help" in js["parameters"]

View File

@@ -1,6 +1,11 @@
import logging
from functools import partial
try:
from unittest.mock import patch
except ImportError:
from mock import patch
logger = logging.getLogger(__name__)
from unittest import TestCase
@@ -12,7 +17,11 @@ class CLITest(TestCase):
def test_basic(self):
self.assertRaises(Error, partial(main_function, []))
res = main_function(['--input', 'test', '--algo', 'rand', '--with-parameters'])
assert res.parameters['input'] == 'test'
assert 'rand' in res.parameters['algorithm']
assert res.parameters['input'] == 'test'
with patch('senpy.extensions.Senpy.analyse') as patched:
main_function(['--input', 'test'])
patched.assert_called_with(input='test')
with patch('senpy.extensions.Senpy.analyse') as patched:
main_function(['--input', 'test', '--algo', 'rand'])
patched.assert_called_with(input='test', algo='rand')

View File

@@ -4,21 +4,18 @@ try:
except ImportError:
from mock import patch
import json
from senpy.client import Client
from senpy.models import Results, Plugins, Error
from senpy.plugins import AnalysisPlugin, default_plugin_type
from senpy.models import Results, Error
class Call(dict):
def __init__(self, obj):
self.obj = obj.serialize()
self.obj = obj.jsonld()
self.status_code = 200
self.content = self.json()
def json(self):
return json.loads(self.obj)
return self.obj
class ModelsTest(TestCase):
@@ -47,19 +44,3 @@ class ModelsTest(TestCase):
method='GET',
params={'input': 'hello',
'algorithm': 'NONEXISTENT'})
def test_plugins(self):
endpoint = 'http://dummy/'
client = Client(endpoint)
plugins = Plugins()
p1 = AnalysisPlugin({'name': 'AnalysisP1', 'version': 0, 'description': 'No'})
plugins.plugins = [p1, ]
success = Call(plugins)
with patch('requests.request', return_value=success) as patched:
response = client.plugins()
assert isinstance(response, dict)
assert len(response) == 1
assert "AnalysisP1" in response
patched.assert_called_with(
url=endpoint + '/plugins', method='GET',
params={'plugin_type': default_plugin_type})

View File

@@ -10,22 +10,15 @@ except ImportError:
from functools import partial
from senpy.extensions import Senpy
from senpy import plugins
from senpy.models import Error, Results, Entry, EmotionSet, Emotion, Plugin
from senpy import api
from senpy.models import Error, Results, Entry, EmotionSet, Emotion
from flask import Flask
from unittest import TestCase
def analyse(instance, **kwargs):
request = api.parse_call(kwargs)
return instance.analyse(request)
class ExtensionsTest(TestCase):
def setUp(self):
self.app = Flask('test_extensions')
self.dir = os.path.dirname(__file__)
self.dir = os.path.join(os.path.dirname(__file__))
self.senpy = Senpy(plugin_folder=self.dir,
app=self.app,
default_plugins=False)
@@ -45,8 +38,8 @@ class ExtensionsTest(TestCase):
print(self.senpy.plugins)
assert "Dummy" in self.senpy.plugins
def test_installing(self):
""" Installing a plugin """
def test_enabling(self):
""" Enabling a plugin """
info = {
'name': 'TestPip',
'module': 'dummy',
@@ -55,31 +48,19 @@ class ExtensionsTest(TestCase):
'version': 0
}
root = os.path.join(self.dir, 'plugins', 'dummy_plugin')
module = plugins.load_plugin_from_info(info, root=root)
plugins.install_deps(info)
assert module.name == 'TestPip'
name, module = self.senpy._load_plugin_from_info(info, root=root)
assert name == 'TestPip'
assert module
import noop
dir(noop)
self.senpy.install_deps()
def test_enabling(self):
def test_installing(self):
""" Enabling a plugin """
self.senpy.activate_all(sync=True)
assert len(self.senpy.plugins) >= 3
assert self.senpy.plugins["Sleep"].is_activated
def test_installing_nonexistent(self):
""" Fail if the dependencies cannot be met """
info = {
'name': 'TestPipFail',
'module': 'dummy',
'description': None,
'requirements': ['IAmMakingThisPackageNameUpToFail'],
'version': 0
}
with self.assertRaises(Error):
plugins.install_deps(info)
def test_disabling(self):
""" Disabling a plugin """
self.senpy.deactivate_all(sync=True)
@@ -97,65 +78,37 @@ class ExtensionsTest(TestCase):
def test_noplugin(self):
""" Don't analyse if there isn't any plugin installed """
self.senpy.deactivate_all(sync=True)
self.assertRaises(Error, partial(analyse, self.senpy, input="tupni"))
self.assertRaises(Error, partial(self.senpy.analyse, input="tupni"))
self.assertRaises(Error,
partial(
self.senpy.analyse,
input="tupni",
algorithm='Dummy'))
def test_analyse(self):
""" Using a plugin """
# I was using mock until plugin started inheriting
# Leaf (defaultdict with __setattr__ and __getattr__.
r1 = analyse(self.senpy, algorithm="Dummy", input="tupni", output="tuptuo")
r2 = analyse(self.senpy, input="tupni", output="tuptuo")
r1 = self.senpy.analyse(
algorithm="Dummy", input="tupni", output="tuptuo")
r2 = self.senpy.analyse(input="tupni", output="tuptuo")
assert r1.analysis[0] == "plugins/Dummy_0.1"
assert r2.analysis[0] == "plugins/Dummy_0.1"
assert r1.entries[0]['nif:iString'] == 'input'
def test_analyse_jsonld(self):
""" Using a plugin with JSON-LD input"""
js_input = '''{
"@id": "prueba",
"@type": "results",
"entries": [
{"@id": "entry1",
"nif:isString": "tupni",
"@type": "entry"
}
]
}'''
r1 = analyse(self.senpy,
algorithm="Dummy",
input=js_input,
informat="json-ld",
output="tuptuo")
r2 = analyse(self.senpy,
input="tupni",
output="tuptuo")
assert r1.analysis[0] == "plugins/Dummy_0.1"
assert r2.analysis[0] == "plugins/Dummy_0.1"
assert r1.entries[0]['nif:iString'] == 'input'
assert r1.entries[0].text == 'input'
def test_analyse_error(self):
mm = mock.MagicMock()
mm.id = 'magic_mock'
mm.is_activated = True
mm.analyse_entries.side_effect = Error('error in analysis', status=500)
mm.analyse_entry.side_effect = Error('error on analysis', status=900)
self.senpy.plugins['MOCK'] = mm
try:
analyse(self.senpy, input='nothing', algorithm='MOCK')
assert False
except Error as ex:
assert 'error in analysis' in ex['message']
assert ex['status'] == 500
resp = self.senpy.analyse(input='nothing', algorithm='MOCK')
assert resp['message'] == 'error on analysis'
assert resp['status'] == 900
mm.analyse.side_effect = Exception('generic exception on analysis')
mm.analyse_entries.side_effect = Exception(
mm.analyse_entry.side_effect = Exception(
'generic exception on analysis')
try:
analyse(self.senpy, input='nothing', algorithm='MOCK')
assert False
except Error as ex:
assert 'generic exception on analysis' in ex['message']
assert ex['status'] == 500
resp = self.senpy.analyse(input='nothing', algorithm='MOCK')
assert resp['message'] == 'generic exception on analysis'
assert resp['status'] == 500
def test_filtering(self):
""" Filtering plugins """
@@ -171,40 +124,40 @@ class ExtensionsTest(TestCase):
assert len(senpy.plugins) > 1
def test_convert_emotions(self):
self.senpy.activate_all(sync=True)
plugin = Plugin({
self.senpy.activate_all()
plugin = {
'id': 'imaginary',
'onyx:usesEmotionModel': 'emoml:fsre-dimensions'
})
}
eSet1 = EmotionSet()
eSet1.prov__wasGeneratedBy = plugin['@id']
eSet1['onyx:hasEmotion'].append(Emotion({
'emoml:arousal': 1,
'emoml:potency': 0,
'emoml:valence': 0
}))
response = Results({
'analysis': [{'plugin': plugin}],
'entries': [Entry({
'nif:iString': 'much ado about nothing',
'text': 'much ado about nothing',
'emotions': [eSet1]
})]
})
params = {'emotionModel': 'emoml:big6',
'conversion': 'full'}
r1 = deepcopy(response)
r1.parameters = params
self.senpy.convert_emotions(r1)
self.senpy.convert_emotions(r1,
plugin,
params)
assert len(r1.entries[0].emotions) == 2
params['conversion'] = 'nested'
r2 = deepcopy(response)
r2.parameters = params
self.senpy.convert_emotions(r2)
self.senpy.convert_emotions(r2,
plugin,
params)
assert len(r2.entries[0].emotions) == 1
assert r2.entries[0].emotions[0]['prov:wasDerivedFrom'] == eSet1
params['conversion'] = 'filtered'
r3 = deepcopy(response)
r3.parameters = params
self.senpy.convert_emotions(r3)
self.senpy.convert_emotions(r3,
plugin,
params)
assert len(r3.entries[0].emotions) == 1
r3.jsonld()

View File

@@ -11,12 +11,8 @@ from senpy.models import (Emotion,
Entry,
Error,
Results,
Sentiment,
Plugins,
Plugin,
from_string,
from_dict)
from senpy import plugins
Sentiment)
from senpy.plugins import SenpyPlugin
from pprint import pprint
@@ -57,8 +53,8 @@ class ModelsTest(TestCase):
assert (received["entries"][0]["nif:isString"] != "Not testing")
def test_id(self):
""" Adding the id after creation should overwrite the automatic ID
"""
''' Adding the id after creation should overwrite the automatic ID
'''
r = Entry()
j = r.jsonld()
assert '@id' in j
@@ -98,32 +94,20 @@ class ModelsTest(TestCase):
r.validate()
def test_plugins(self):
self.assertRaises(Error, plugins.Plugin)
p = plugins.Plugin({"name": "dummy",
"version": 0,
"extra_params": {
"none": {
"options": ["es", ],
"required": False,
"default": "0"
}
}})
self.assertRaises(Error, SenpyPlugin)
p = SenpyPlugin({"name": "dummy", "version": 0})
c = p.jsonld()
assert '@type' in c
assert c['@type'] == 'plugin'
assert 'info' not in c
assert 'repo' not in c
assert 'extra_params' in c
logging.debug('Framed:')
assert "info" not in c
assert "repo" not in c
assert "extra_params" in c
logging.debug("Framed:")
logging.debug(c)
p.validate()
assert 'es' in c['extra_params']['none']['options']
assert isinstance(c['extra_params']['none']['options'], list)
def test_str(self):
"""The string representation shouldn't include private variables"""
r = Results()
p = plugins.Plugin({"name": "STR test", "version": 0})
p = SenpyPlugin({"name": "STR test", "version": 0})
p._testing = 0
s = str(p)
assert "_testing" not in s
@@ -159,40 +143,3 @@ class ModelsTest(TestCase):
print(t)
g = rdflib.Graph().parse(data=t, format='turtle')
assert len(g) == len(triples)
def test_plugin_list(self):
"""The plugin list should be of type \"plugins\""""
plugs = Plugins()
c = plugs.jsonld()
assert '@type' in c
assert c['@type'] == 'plugins'
def test_single_plugin(self):
"""A response with a single plugin should still return a list"""
plugs = Plugins()
p = Plugin({'id': str(1),
'version': 0,
'description': 'dummy'})
plugs.plugins.append(p)
assert isinstance(plugs.plugins, list)
js = plugs.jsonld()
assert isinstance(js['plugins'], list)
def test_from_string(self):
results = {
'@type': 'results',
'@id': 'prueba',
'entries': [{
'@id': 'entry1',
'@type': 'entry',
'nif:isString': 'TEST'
}]
}
recovered = from_dict(results)
assert isinstance(recovered, Results)
assert isinstance(recovered.entries[0], Entry)
string = json.dumps(results)
recovered = from_string(string)
assert isinstance(recovered, Results)
assert isinstance(recovered.entries[0], Entry)

View File

@@ -6,12 +6,11 @@ import shutil
import tempfile
from unittest import TestCase
from senpy.models import Results, Entry, EmotionSet, Emotion
from senpy import plugins
from senpy.plugins.conversion.emotion.centroids import CentroidConversion
from senpy.models import Results, Entry
from senpy.plugins import SentimentPlugin, ShelfMixin
class ShelfDummyPlugin(plugins.SentimentPlugin, plugins.ShelfMixin):
class ShelfDummyPlugin(SentimentPlugin, ShelfMixin):
def activate(self, *args, **kwargs):
if 'counter' not in self.sh:
self.sh['counter'] = 0
@@ -33,6 +32,7 @@ class PluginsTest(TestCase):
def tearDown(self):
if os.path.exists(self.shelf_dir):
shutil.rmtree(self.shelf_dir)
if os.path.isfile(self.shelf_file):
os.remove(self.shelf_file)
@@ -50,29 +50,26 @@ class PluginsTest(TestCase):
def test_shelf(self):
''' A shelf is created and the value is stored '''
newfile = self.shelf_file + "new"
a = ShelfDummyPlugin(info={
'name': 'shelve',
'version': 'test',
'shelf_file': newfile
'shelf_file': self.shelf_file
})
assert a.sh == {}
a.activate()
assert a.sh == {'counter': 0}
assert a.shelf_file == newfile
assert a.shelf_file == self.shelf_file
a.sh['a'] = 'fromA'
assert a.sh['a'] == 'fromA'
a.save()
sh = pickle.load(open(newfile, 'rb'))
sh = pickle.load(open(self.shelf_file, 'rb'))
assert sh['a'] == 'fromA'
def test_dummy_shelf(self):
with open(self.shelf_file, 'wb') as f:
pickle.dump({'counter': 99}, f)
a = ShelfDummyPlugin(info={
'name': 'DummyShelf',
'shelf_file': self.shelf_file,
@@ -82,47 +79,11 @@ class PluginsTest(TestCase):
assert a.shelf_file == self.shelf_file
res1 = a.analyse(input=1)
assert res1.entries[0].nif__isString == 100
a.deactivate()
del a
assert res1.entries[0].nif__isString == 1
res2 = a.analyse(input=1)
assert res2.entries[0].nif__isString == 2
with open(self.shelf_file, 'rb') as f:
sh = pickle.load(f)
assert sh['counter'] == 100
def test_corrupt_shelf(self):
''' Reusing the values of a previous shelf '''
emptyfile = os.path.join(self.shelf_dir, "emptyfile")
invalidfile = os.path.join(self.shelf_dir, "invalid_file")
with open(emptyfile, 'w+b'), open(invalidfile, 'w+b') as inf:
inf.write(b'ohno')
files = {emptyfile: ['empty file', (EOFError, IndexError)],
invalidfile: ['invalid file', (pickle.UnpicklingError, IndexError)]}
for fn in files:
with open(fn, 'rb') as f:
msg, error = files[fn]
a = ShelfDummyPlugin(info={
'name': 'shelve',
'version': 'test',
'shelf_file': f.name
})
assert os.path.isfile(a.shelf_file)
print('Shelf file: %s' % a.shelf_file)
with self.assertRaises(error):
a.sh['a'] = 'fromA'
a.save()
del a._sh
assert os.path.isfile(a.shelf_file)
a.force_shelf = True
a.sh['a'] = 'fromA'
a.save()
b = pickle.load(f)
assert b['a'] == 'fromA'
def test_reuse_shelf(self):
def test_two(self):
''' Reusing the values of a previous shelf '''
a = ShelfDummyPlugin(info={
'name': 'shelve',
@@ -159,77 +120,3 @@ class PluginsTest(TestCase):
}
})
assert 'example' in a.extra_params
def test_conversion_centroids(self):
info = {
"name": "CentroidTest",
"description": "Centroid test",
"version": 0,
"centroids": {
"c1": {"V1": 0.5,
"V2": 0.5},
"c2": {"V1": -0.5,
"V2": 0.5},
"c3": {"V1": -0.5,
"V2": -0.5},
"c4": {"V1": 0.5,
"V2": -0.5}},
"aliases": {
"V1": "X-dimension",
"V2": "Y-dimension"
},
"centroids_direction": ["emoml:big6", "emoml:fsre-dimensions"]
}
c = CentroidConversion(info)
print(c.serialize())
es1 = EmotionSet()
e1 = Emotion()
e1.onyx__hasEmotionCategory = "c1"
es1.onyx__hasEmotion.append(e1)
res = c._forward_conversion(es1)
assert res["X-dimension"] == 0.5
assert res["Y-dimension"] == 0.5
print(res)
e2 = Emotion()
e2.onyx__hasEmotionCategory = "c2"
es1.onyx__hasEmotion.append(e2)
res = c._forward_conversion(es1)
assert res["X-dimension"] == 0
assert res["Y-dimension"] == 1
print(res)
e = Emotion()
e["X-dimension"] = -0.2
e["Y-dimension"] = -0.3
res = c._backwards_conversion(e)
assert res["onyx:hasEmotionCategory"] == "c3"
print(res)
e = Emotion()
e["X-dimension"] = -0.2
e["Y-dimension"] = 0.3
res = c._backwards_conversion(e)
assert res["onyx:hasEmotionCategory"] == "c2"
def make_mini_test(plugin_info):
def mini_test(self):
plugin = plugins.load_plugin_from_info(plugin_info, install=True)
plugin.test()
return mini_test
def _add_tests():
root = os.path.dirname(__file__)
plugs = plugins.load_plugins(os.path.join(root, ".."), loader=plugins.parse_plugin_info)
for k, v in plugs.items():
pass
t_method = make_mini_test(v)
t_method.__name__ = 'test_plugin_{}'.format(k)
setattr(PluginsTest, t_method.__name__, t_method)
del t_method
_add_tests()

View File

@@ -34,8 +34,7 @@ def do_create_(jsfile, success):
except (AssertionError, ValidationError, KeyError) as ex:
if success:
raise
return
assert success
return do_expected