Change name to split, according to issue #37

* Add git fetch to (try to) fix github push from gitlab

.gitlab-ci.yml

@@ -1,18 +1,19 @@
-image: gsiupm/dockermake:latest
+# Uncomment if you want to use docker-in-docker
-
+# image: gsiupm/dockermake:latest
-
+# services:
+# - docker:dind
 # 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:
+  - docker login -u $HUB_USER -p $HUB_PASSWORD
+
 .test: &test_definition
   stage: test
   script:
@@ -28,11 +29,8 @@ 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:
@@ -57,9 +55,52 @@ push-latest:
     - master
     - triggers
 
+push-github:
+  stage: deploy
+  script:
+    - make -e push-github
+  only:
+    - master
+    - triggers
+
+deploy_pypi:
+  stage: deploy
+  script:   # Configure the PyPI credentials, then push the package, and cleanup the creds.
+    - echo "[server-login]" >> ~/.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
+
+push-github:
+  stage: deploy
+  script:
+    - make -e push-github
+  only:
+    - master
+    - triggers
+
 clean :
   stage: clean
   script:
     - make -e clean
-  only:
+  when: manual
-    - master
+
+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

.travis.yml

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

Dockerfile.template

@@ -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-deps --no-index .
+RUN pip install --no-index --no-deps --editable .
 
 ENTRYPOINT ["python", "-m", "senpy", "-f", "/senpy-plugins/", "--host", "0.0.0.0"]

Makefile

@@ -1,12 +1,30 @@
+NAME=senpy
+VERSION=$(shell git describe --tags --dirty 2>/dev/null)
+GITHUB_REPO=git@github.com:gsi-upm/senpy.git
+
+IMAGENAME=gsiupm/senpy
+IMAGEWTAG=$(IMAGENAME):$(VERSION)
+
 PYVERSIONS=3.5 2.7
 PYMAIN=$(firstword $(PYVERSIONS))
-NAME=senpy
+
-REPO=gsiupm
+DEVPORT=5000
-VERSION=$(shell git describe --tags --dirty 2>/dev/null)
+
 TARNAME=$(NAME)-$(VERSION).tar.gz 
-IMAGENAME=$(REPO)/$(NAME)
-IMAGEWTAG=$(IMAGENAME):$(VERSION)
 action="test-${PYMAIN}"
+GITHUB_REPO=git@github.com:gsi-upm/senpy.git
+
+KUBE_CA_PEM_FILE=""
+KUBE_URL=""
+KUBE_TOKEN=""
+KUBE_NAMESPACE=$(NAME)
+KUBECTL=docker run --rm -v $(KUBE_CA_PEM_FILE):/tmp/ca.pem -v $$PWD:/tmp/cwd/ -i lachlanevenson/k8s-kubectl --server="$(KUBE_URL)" --token="$(KUBE_TOKEN)" --certificate-authority="/tmp/ca.pem" -n $(KUBE_NAMESPACE)
+CI_REGISTRY=docker.io
+CI_REGISTRY_USER=gitlab
+CI_BUILD_TOKEN=""
+CI_COMMIT_REF_NAME=master
+
+
 
 all: build run
 
@@ -17,7 +35,7 @@ version: .FORCE
 	@echo $(VERSION)
 
 yapf:
-	yapf -i -r senpy
+	yapf -i -r $(NAME)
 	yapf -i -r tests
 
 init:
@@ -36,14 +54,14 @@ quick_build: $(addprefix build-, $(PYMAIN))
 build: $(addprefix build-, $(PYVERSIONS))
 
 build-%: version Dockerfile-%
-	docker build -t '$(IMAGEWTAG)-python$*' -f Dockerfile-$* .;
+	docker build -t '$(IMAGEWTAG)-python$*' --cache-from $(IMAGENAME):python$* -f Dockerfile-$* .;
 
 quick_test: $(addprefix test-,$(PYMAIN))
 
 dev-%:
 	@docker start $(NAME)-dev$* || (\
 		$(MAKE) build-$*; \
-		docker run -d -w /usr/src/app/ -v $$PWD:/usr/src/app --entrypoint=/bin/bash -ti --name $(NAME)-dev$* '$(IMAGEWTAG)-python$*'; \
+		docker run -d -w /usr/src/app/ -p $(DEVPORT):5000 -v $$PWD:/usr/src/app --entrypoint=/bin/bash -ti --name $(NAME)-dev$* '$(IMAGEWTAG)-python$*'; \
 	)\
 
 	docker exec -ti $(NAME)-dev$* bash
@@ -52,26 +70,29 @@ dev: dev-$(PYMAIN)
 
 test-all: $(addprefix test-,$(PYVERSIONS))
 
-test-%: build-%
+test-%:
-	docker run --rm --entrypoint /usr/local/bin/python -w /usr/src/app $(IMAGEWTAG)-python$*  setup.py test
+	docker run --rm --entrypoint /usr/local/bin/python -w /usr/src/app $(IMAGENAME):python$*  setup.py test
 
 test: test-$(PYMAIN)
 
-dist/$(TARNAME):
+dist/$(TARNAME): version
-	docker run --rm -ti -v $$PWD:/usr/src/app/ -w /usr/src/app/ python:$(PYMAIN) python setup.py sdist;
+	python setup.py sdist;
 
 sdist: dist/$(TARNAME)
 
 pip_test-%: sdist
-	docker run --rm -v $$PWD/dist:/dist/ -ti python:$* pip install /dist/$(TARNAME);
+	docker run --rm -v $$PWD/dist:/dist/ python:$* pip install /dist/$(TARNAME);
 
 pip_test: $(addprefix pip_test-,$(PYVERSIONS))
 
-clean:
+pip_upload: pip_test 
-	@docker ps -a | awk '/$(REPO)\/$(NAME)/{ split($$2, vers, "-"); if(vers[0] != "${VERSION}"){ print $$1;}}' | xargs docker rm -v 2>/dev/null|| true
+	python setup.py sdist upload ;
-	@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
 
+clean:
+	@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
+	@docker stop $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
+	@docker rm $(addprefix $(NAME)-dev,$(PYVERSIONS)) 2>/dev/null || true
 
 git_commit:
 	git commit -a
@@ -82,26 +103,45 @@ git_tag:
 git_push:
 	git push --tags origin master
 
-pip_upload:
-	python setup.py sdist upload ;
-
-pip_test: $(addprefix pip_test-,$(PYVERSIONS))
-
 run-%: build-%
-	docker run --rm -p 5000:5000 -ti '$(IMAGEWTAG)-python$(PYMAIN)' --default-plugins
+	docker run --rm -p $(DEVPORT):5000 -ti '$(IMAGEWTAG)-python$(PYMAIN)' --default-plugins
 
 run: run-$(PYMAIN)
 
-push-latest: build-$(PYMAIN)
+push-latest: $(addprefix push-latest-,$(PYVERSIONS))
 	docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
 	docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGENAME)'
-	docker push '$(IMAGENAME)'
+	docker push '$(IMAGENAME):latest'
 	docker push '$(IMAGEWTAG)'
 
+push-latest-%: build-%
+	docker tag $(IMAGENAME):$(VERSION)-python$* $(IMAGENAME):python$*
+	docker push $(IMAGENAME):$(VERSION)-python$*
+	docker push $(IMAGENAME):python$*
+
 push-%: build-%
 	docker push $(IMAGENAME):$(VERSION)-python$*
 
+push: $(addprefix push-,$(PYVERSIONS))
+	docker tag '$(IMAGEWTAG)-python$(PYMAIN)' '$(IMAGEWTAG)'
+	docker push  $(IMAGENAME):$(VERSION)
+
+push-github:
+	$(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) || true
+	@GIT_SSH_COMMAND="ssh -i $(KEY_FILE)" git push github-deploy $(CI_COMMIT_REF_NAME)
+	rm $(KEY_FILE)
+
 ci:
 	gitlab-runner exec docker --docker-volumes /var/run/docker.sock:/var/run/docker.sock --env CI_PROJECT_NAME=$(NAME) ${action}
 
-.PHONY: test test-% test-all build-% build test pip_test run yapf push-main push-% dev ci version .FORCE
+deploy:
+	@$(KUBECTL) delete secret $(CI_REGISTRY) || true
+	@$(KUBECTL) create secret docker-registry $(CI_REGISTRY) --docker-server=$(CI_REGISTRY) --docker-username=$(CI_REGISTRY_USER) --docker-email=$(CI_REGISTRY_USER) --docker-password=$(CI_BUILD_TOKEN)
+	@$(KUBECTL) apply -f /tmp/cwd/k8s/
+
+
+.PHONY: test test-% test-all build-% build test pip_test run yapf push-main push-% dev ci version .FORCE deploy

README.rst

@@ -23,7 +23,7 @@ Through PIP
 
 .. code:: bash
 
-   pip install --user senpy
+   pip install -U --user senpy
 
    
 Alternatively, you can use the development version:
@@ -42,6 +42,53 @@ 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
 -----
 
@@ -49,12 +96,14 @@ 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
 
 

docs/SenpyClientUse.ipynb

@@ -0,0 +1,317 @@
+{
+ "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
+}

docs/about.rst

@@ -0,0 +1,11 @@
+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.

docs/api.rst

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

docs/apischema.rst

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

docs/bad-examples/results/example-analysis-as-id-FAIL.json

@@ -0,0 +1,78 @@
+{
+  "@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": "wrong"
+    }
+  ],
+  "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"
+            }
+          ]
+        }
+      ]
+    }
+  ]
+}

docs/commandline.rst

@@ -0,0 +1,9 @@
+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

docs/conf.py

@@ -37,6 +37,7 @@ extensions = [
     'sphinx.ext.todo',
     'sphinxcontrib.httpdomain',
     'sphinx.ext.coverage',
+    'sphinx.ext.autosectionlabel',
 ]
 
 # Add any paths that contain templates here, relative to this directory.
@@ -54,20 +55,21 @@ 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:
+# with open('../senpy/VERSION') as f:
-    version = f.read().strip()
+#     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:
@@ -104,14 +106,14 @@ 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
+# if not on_rtd:  # only import and set the theme if we're building docs locally
-    import sphinx_rtd_theme
+#     import sphinx_rtd_theme
-    html_theme = 'sphinx_rtd_theme'
+#     html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
-    html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
 
-else:
+# else:
-    html_theme = 'default'
+#     html_theme = 'default'
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
@@ -119,7 +121,13 @@ else:
 # 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 = {}
+html_theme_options = {
+    'logo': 'header.png',
+    'github_user': 'gsi-upm',
+    'github_repo': 'senpy',
+    'github_banner': True,
+}
+
 
 # Add any paths that contain custom themes here, relative to this directory.
 #html_theme_path = []
@@ -159,7 +167,13 @@ html_static_path = ['_static']
 #html_use_smartypants = True
 
 # Custom sidebar templates, maps document names to template names.
-#html_sidebars = {}
+html_sidebars = {
+    '**': [
+        'about.html',
+        'navigation.html',
+        'searchbox.html',
+        ]
+    }
 
 # Additional templates that should be rendered to pages, maps page names to
 # template names.

docs/conversion.rst

@@ -1,13 +1,13 @@
-Introduction
+Conversion
-------------
+----------
 
 Senpy includes experimental support for emotion/sentiment conversion plugins.
 
 
 Use
----
+===
 
-Consider the original query: `http://127.0.0.1:5000/api/?i=hello&algo=emoRand`_
+Consider the original query: http://127.0.0.1:5000/api/?i=hello&algo=emoRand
 
 The requested plugin (emoRand) returns emotions using Ekman's model (or big6 in EmotionML):
 
@@ -28,7 +28,7 @@ The requested plugin (emoRand) returns emotions using Ekman's model (or big6 in
 
 To get these emotions in VAD space (FSRE dimensions in EmotionML), we'd do this:
 
-`http://127.0.0.1:5000/api/?i=hello&algo=emoRand&emotionModel=emoml:fsre-dimensions`_
+http://127.0.0.1:5000/api/?i=hello&algo=emoRand&emotionModel=emoml:fsre-dimensions
 
 This call, provided there is a valid conversion plugin from Ekman's to VAD, would return something like this:
 
@@ -87,7 +87,7 @@ It is also possible to get the original emotion nested within the new converted
 Lastly, `conversion=filtered` would only return the converted emotions.
 
 Developing a conversion plugin
-------------------------------
+================================
 
 Conversion plugins are discovered by the server just like any other plugin.
 The difference is the slightly different API, and the need to specify the `source` and `target` of the conversion.

docs/demo.rst

@@ -1,7 +1,8 @@
 Demo
 ----
 
-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.
+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.
 
 .. image:: senpy-playground.png
   :height: 400px
@@ -12,64 +13,4 @@ There is a demo available on http://senpy.demos.gsi.dit.upm.es/, where you can a
 Plugins Demo
 ============
 
-The next plugins are available at the 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/.
-
-* 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

docs/examples.rst

@@ -0,0 +1,78 @@
+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

docs/examples/results/example-analysis-as-id.json

@@ -0,0 +1,74 @@
+{
+  "@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"
+            }
+          ]
+        }
+      ]
+    }
+  ]
+}

docs/index.rst

@@ -1,19 +1,35 @@
-.. Senpy documentation master file, created by
-   sphinx-quickstart on Tue Feb 24 08:57:32 2015.
-   You can adapt this file completely to your liking, but it should at least
-   contain the root `toctree` directive.
-
 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/
 
-Contents:
+
+
+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
 
 .. toctree::
+   :caption: Learn more about senpy:
+   :maxdepth: 2
+
    senpy
    installation
-   usage
-   api
-   schema
-   plugins
    demo
-   :maxdepth: 2
+   usage
+   apischema
+   plugins
+   conversion
+   about

docs/installation.rst

@@ -1,6 +1,16 @@
 Installation
 ------------
-The stable version can be installed in three ways.
+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.
+
 
 Through PIP
 ***********
@@ -22,6 +32,41 @@ 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: ``docker run -ti -p 5000:5000 gsiupm/senpy --host 0.0.0.0 --default-plugins``.
+Build the image or use the pre-built one:   
 
-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``
+.. 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

docs/plugins.rst

@@ -2,27 +2,36 @@ Developing new plugins
 ----------------------
 This document describes how to develop a new analysis plugin. For an example of conversion plugins, see :doc:`conversion`.
 
-Each plugin represents a different analysis process.There are two types of files that are needed by senpy for loading a plugin:
+A more step-by-step tutorial with slides is available `here <https://lab.cluster.gsi.dit.upm.es/senpy/senpy-tutorial>`__ 
 
-- Definition file, has the ".senpy" extension.
+.. contents:: :local:
-- Code file, is a python file.
 
-This separation will allow us to deploy plugins that use the same code but employ different parameters.
+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.
 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.
 
-Plugins Definitions
+Plugin Definition files
-===================
+=======================
 
 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: 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:
+* 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:
 
   .. code:: yaml
 
@@ -68,10 +77,28 @@ 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 in the parameters supplied by a user and should yield one or more ``Entry`` objects.
+* 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.
 
 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
 ==============
@@ -88,7 +115,7 @@ The definition file would look like this:
           module: helloworld
           version: 0.0
           threshold: 10
-
+          description: Hello World
 
 Now, in a file named ``helloworld.py``:
 
@@ -97,11 +124,11 @@ Now, in a file named ``helloworld.py``:
           #!/bin/env python
           #helloworld.py
 
-          from senpy.plugins import SenpyPlugin
+          from senpy.plugins import AnalysisPlugin
           from senpy.models import Sentiment
 
 
-          class HelloWorld(SenpyPlugin):
+          class HelloWorld(AnalysisPlugin):
 
               def analyse_entry(entry, params):
                   '''Basically do nothing with each entry'''
@@ -114,15 +141,112 @@ 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 conveersion plugin may leave out those entries that do not contain relevant information.
+On the other hand, a conversion plugin may leave out those entries that do not contain relevant information.
 
 
 If I'm using a classifier, where should I train it?
@@ -132,9 +256,9 @@ Training a classifier can be time time consuming. To avoid running the training
 
 .. code:: python
 
-          from senpy.plugins import ShelfMixin, SenpyPlugin
+          from senpy.plugins import ShelfMixin, AnalysisPlugin
 
-          class MyPlugin(ShelfMixin, SenpyPlugin):
+          class MyPlugin(ShelfMixin, AnalysisPlugin):
               def train(self):
                   ''' Code to train the classifier
                   '''
@@ -151,12 +275,16 @@ Training a classifier can be time time consuming. To avoid running the training
               def deactivate(self):
                   self.close()
 
-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.
+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.
 
-I want to implement my service as a plugin, How i can do it?
+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.
 
-This example ilustrate how to implement the Sentiment140 service as a plugin in senpy
+How can I turn an external service into a plugin?
+?????????????????????????????????????????????????
+
+This example ilustrate how to implement a plugin that accesses the Sentiment140 service.
 
 .. code:: python
 
@@ -190,26 +318,30 @@ This example ilustrate how to implement the Sentiment140 service as a plugin in
                   yield entry
 
 
-Where can I define extra parameters to be introduced in the request to my plugin?
+Can my plugin require additional parameters from the user?
-?????????????????????????????????????????????????????????????????????????????????
+??????????????????????????????????????????????????????????
 
-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:
+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:
 
 * aliases: the different names which can be used in the request to use the parameter.
-* required: this option is a boolean and indicates if the parameters is binding in operation plugin.
+* required: if set to true, users need to provide this parameter unless a default is set.
-* options: the different values of the paremeter.
+* 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, this is useful in case the paremeter is required and you want to have a default value.
+* default: the default value of the parameter, if none is provided in the request.
 
 .. code:: python
 
-          "extra_params": {
+          extra_params
-             "language": {
+             language:
-                "aliases": ["language", "l"],
+                aliases:
-                "required": true,
+                    - language
-                "options": ["es","en"],
+                    - lang
-                "default": "es"
+                    - 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.
@@ -241,7 +373,6 @@ Additionally, with the ``--pdb`` option you will be dropped into a pdb post mort
 
    senpy --pdb
 
-
 Where can I find more code examples?
 ????????????????????????????????????
 

docs/requirements.txt

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

docs/schema.rst

@@ -1,74 +0,0 @@
-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

docs/senpy.rst

@@ -1,20 +1,38 @@
 What is Senpy?
 --------------
 
-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. 
+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.
 
-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. 
+.. image:: senpy-framework.png
+  :width: 60%
+  :align: center
 
-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.
 
-Specifications
+Senpy for end users
-==============
+===================
 
-The model used in Senpy is based on the following 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`.
 
-* 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.
+Senpy for service developers
-* NIF 2.0, which defines a semantic format and APO for improving interoperability among natural language processing services
+============================
+
+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.
 
 Architecture
 ============
@@ -29,7 +47,5 @@ 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
-  :height: 400px
+  :width: 100%
-  :width: 800px
-  :scale: 100 %
   :align: center

docs/server.rst

@@ -0,0 +1,58 @@
+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.

docs/usage.rst

@@ -1,76 +1,15 @@
 Usage
 -----
 
-The easiest and recommended way is to just use the command-line tool to load your plugins and launch the server.
+First of all, you need to install the package.
+See :doc:`installation` for instructions.
+Once installed, the `senpy` command should be available. 
 
-.. code:: bash
+.. toctree::
+   :maxdepth: 1
 
-   senpy
+   server
-
+   SenpyClientUse
-Or, alternatively:
+   commandline
-
-.. 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
-

docs/vocabularies.rst

@@ -0,0 +1,8 @@
+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

k8s/README.md

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

k8s/senpy-deployment.yaml

@@ -0,0 +1,26 @@
+---
+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

k8s/senpy-ingress.yaml

@@ -0,0 +1,14 @@
+---
+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

k8s/senpy-svc.yaml

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

requirements.txt

@@ -1,6 +1,6 @@
 Flask>=0.10.1
 requests>=2.4.1
-gevent>=1.1rc4
+tornado>=4.4.3
 PyLD>=0.6.5
 six
 future

senpy/__init__.py

@@ -17,7 +17,6 @@
 """
 Sentiment analysis server in Python
 """
-from __future__ import print_function
 from .version import __version__
 
 import logging

senpy/__main__.py

@@ -22,35 +22,15 @@ 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(
@@ -94,28 +74,38 @@ 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)
     if args.only_install:
         sp.install_deps()
         return
     sp.activate_all()
-    http_server = WSGIServer((args.host, args.port), app)
+    print('Senpy version {}'.format(senpy.__version__))
-    try:
+    print('Server running on port %s:%d. Ctrl+C to quit' % (args.host,
-        print('Senpy version {}'.format(senpy.__version__))
+                                                            args.port))
-        print('Server running on port %s:%d. Ctrl+C to quit' % (args.host,
+    app.run(args.host,
-                                                                args.port))
+            args.port,
-        http_server.serve_forever()
+            threaded=args.threaded,
-    except KeyboardInterrupt:
+            debug=app.debug)
-        print('Bye!')
-    http_server.stop()
     sp.deactivate_all()
 
 

senpy/api.py

@@ -26,6 +26,13 @@ API_PARAMS = {
         "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",
@@ -63,7 +70,7 @@ NIF_PARAMS = {
         "aliases": ["f", "informat"],
         "required": False,
         "default": "text",
-        "options": ["turtle", "text"],
+        "options": ["turtle", "text", "json-ld"],
     },
     "intype": {
         "@id": "intype",

senpy/blueprints.py

@@ -25,6 +25,7 @@ from .version import __version__
 from functools import wraps
 
 import logging
+import json
 
 logger = logging.getLogger(__name__)
 
@@ -74,7 +75,7 @@ def basic_api(f):
     @wraps(f)
     def decorated_function(*args, **kwargs):
         raw_params = get_params(request)
-        headers = {'X-ORIGINAL-PARAMS': raw_params}
+        headers = {'X-ORIGINAL-PARAMS': json.dumps(raw_params)}
         # Get defaults
         web_params = parse_params({}, spec=WEB_PARAMS)
         api_params = parse_params({}, spec=API_PARAMS)
@@ -92,6 +93,9 @@ def basic_api(f):
             response = f(*args, **kwargs)
         except Error as ex:
             response = ex
+            logger.error(ex)
+            if current_app.debug:
+                raise
 
         in_headers = web_params['inHeaders'] != "0"
         expanded = api_params['expanded-jsonld']
@@ -121,7 +125,9 @@ def api():
 @basic_api
 def plugins():
     sp = current_app.senpy
-    dic = Plugins(plugins=list(sp.plugins.values()))
+    ptype = request.params.get('plugin_type')
+    plugins = sp.filter_plugins(plugin_type=ptype)
+    dic = Plugins(plugins=list(plugins.values()))
     return dic
 
 

senpy/client.py

@@ -1,6 +1,7 @@
 import requests
 import logging
 from . import models
+from .plugins import default_plugin_type
 
 logger = logging.getLogger(__name__)
 
@@ -12,12 +13,15 @@ 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'

senpy/extensions.py

@@ -5,8 +5,9 @@ It orchestrates plugin (de)activation and analysis.
 from future import standard_library
 standard_library.install_aliases()
 
-from .plugins import SentimentPlugin, SenpyPlugin
+from . import plugins
-from .models import Error, Entry, Results
+from .plugins import SenpyPlugin
+from .models import Error, Entry, Results, from_string
 from .blueprints import api_blueprint, demo_blueprint, ns_blueprint
 from .api import API_PARAMS, NIF_PARAMS, parse_params
 
@@ -21,11 +22,18 @@ import importlib
 import logging
 import traceback
 import yaml
-import pip
+import subprocess
 
 logger = logging.getLogger(__name__)
 
 
+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)
+
+
 class Senpy(object):
     """ Default Senpy extension for Flask """
 
@@ -77,74 +85,105 @@ class Senpy(object):
         else:
             logger.debug("Not a folder: %s", folder)
 
-    def _find_plugin(self, params):
+    def _find_plugins(self, params):
-        api_params = parse_params(params, spec=API_PARAMS)
+        if not self.analysis_plugins:
-        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.").format(algo))
+                         " Please install one."))
-        if algo not in self.plugins:
+        api_params = parse_params(params, spec=API_PARAMS)
-            logger.debug(("The algorithm '{}' is not valid\n"
+        algos = None
-                          "Valid algorithms: {}").format(algo,
+        if "algorithm" in api_params and api_params["algorithm"]:
-                                                         self.plugins.keys()))
+            algos = api_params["algorithm"].split(',')
+        elif self.default_plugin:
+            algos = [self.default_plugin.name, ]
+        else:
             raise Error(
                 status=404,
-                message="The algorithm '{}' is not valid".format(algo))
+                message="No default plugin found, and None provided")
 
-        if not self.plugins[algo].is_activated:
+        plugins = list()
-            logger.debug("Plugin not activated: {}".format(algo))
+        for algo in algos:
-            raise Error(
+            if algo not in self.plugins:
-                status=400,
+                logger.debug(("The algorithm '{}' is not valid\n"
-                message=("The algorithm '{}'"
+                              "Valid algorithms: {}").format(algo,
-                         " is not activated yet").format(algo))
+                                                             self.plugins.keys()))
-        return self.plugins[algo]
+                raise Error(
+                    status=404,
+                    message="The algorithm '{}' is not valid".format(algo))
 
-    def _get_params(self, params, plugin):
+            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))
+            plugins.append(self.plugins[algo])
+        return plugins
+
+    def _get_params(self, params, plugin=None):
         nif_params = parse_params(params, spec=NIF_PARAMS)
-        extra_params = plugin.get('extra_params', {})
+        if plugin:
-        specific_params = parse_params(params, spec=extra_params)
+            extra_params = plugin.get('extra_params', {})
-        nif_params.update(specific_params)
+            specific_params = parse_params(params, spec=extra_params)
+            nif_params.update(specific_params)
         return nif_params
 
     def _get_entries(self, params):
-        entry = None
         if params['informat'] == 'text':
+            results = Results()
             entry = Entry(text=params['input'])
+            results.entries.append(entry)
+        elif params['informat'] == 'json-ld':
+            results = from_string(params['input'], cls=Results)
         else:
-            raise NotImplemented('Only text input format implemented')
+            raise NotImplemented('Informat {} is not implemented'.format(params['informat']))
-        yield entry
+        return results
+
+    def _process_entries(self, entries, plugins, nif_params):
+        if not plugins:
+            for i in entries:
+                yield i
+            return
+        plugin = plugins[0]
+        specific_params = self._get_params(nif_params, plugin)
+        results = plugin.analyse_entries(entries, specific_params)
+        for i in self._process_entries(results, plugins[1:], nif_params):
+            yield i
+
+    def _process_response(self, resp, plugins, nif_params):
+        entries = resp.entries
+        resp.entries = []
+        for plug in plugins:
+            resp.analysis.append(plug.id)
+        for i in self._process_entries(entries, plugins, nif_params):
+            resp.entries.append(i)
+        return resp
 
     def analyse(self, **api_params):
+        """
+        Main method that analyses a request, either from CLI or HTTP.
+        It uses a dictionary of parameters, provided by the user.
+        """
         logger.debug("analysing with params: {}".format(api_params))
-        plugin = self._find_plugin(api_params)
+        plugins = self._find_plugins(api_params)
-        nif_params = self._get_params(api_params, plugin)
+        nif_params = self._get_params(api_params)
-        resp = Results()
+        resp = self._get_entries(nif_params)
         if 'with_parameters' in api_params:
             resp.parameters = nif_params
         try:
-            entries = []
+            resp = self._process_response(resp, plugins, nif_params)
-            for i in self._get_entries(nif_params):
+            self.convert_emotions(resp, plugins, 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:
+        except (Error, Exception) as ex:
+            if not isinstance(ex, Error):
+                ex = Error(message=str(ex), status=500)
             logger.exception('Error returning analysis result')
-            resp = ex
+            raise 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(**{'@type': 'emotionConversionPlugin'})
+        candidates = self.filter_plugins(plugin_type='emotionConversionPlugin')
         for name, candidate in candidates.items():
             for pair in candidate.onyx__doesConversion:
                 logging.debug(pair)
@@ -154,30 +193,32 @@ class Senpy(object):
                     # logging.debug('Found candidate: {}'.format(candidate))
                     yield candidate
 
-    def convert_emotions(self, resp, plugin, params):
+    def convert_emotions(self, resp, plugins, params):
         """
-        Conversion of all emotions in a response.
+        Conversion of all emotions in a response **in place**.
         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
         """
-        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
-        try:
+
-            candidate = next(self._conversion_candidates(fromModel, toModel))
+        logger.debug('Asked for model: {}'.format(toModel))
-        except StopIteration:
+        output = params.get('conversion', None)
-            e = Error(('No conversion plugin found for: '
+        candidates = {}
-                       '{} -> {}'.format(fromModel, toModel)))
+        for plugin in plugins:
-            e.original_response = resp
+            try:
-            e.parameters = params
+                fromModel = plugin.get('onyx:usesEmotionModel', None)
-            raise e
+                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
         newentries = []
         for i in resp.entries:
             if output == "full":
@@ -185,6 +226,9 @@ class Senpy(object):
             else:
                 newemotions = []
             for j in i.emotions:
+                plugname = j['prov:wasGeneratedBy']
+                candidate = candidates[plugname]
+                resp.analysis.append(candidate.id)
                 for k in candidate.convert(j, fromModel, toModel, params):
                     k.prov__wasGeneratedBy = candidate.id
                     if output == 'nested':
@@ -193,13 +237,14 @@ class Senpy(object):
             i.emotions = newemotions
             newentries.append(i)
         resp.entries = newentries
-        resp.analysis.append(candidate.id)
+        resp.analysis = list(set(resp.analysis))
 
     @property
     def default_plugin(self):
         candidate = self._default
         if not candidate:
-            candidates = self.filter_plugins(is_activated=True)
+            candidates = self.filter_plugins(plugin_type='analysisPlugin',
+                                             is_activated=True)
             if len(candidates) > 0:
                 candidate = list(candidates.values())[0]
         logger.debug("Default: {}".format(candidate))
@@ -258,6 +303,7 @@ class Senpy(object):
         else:
             th = Thread(target=act)
             th.start()
+            return th
 
     def deactivate_plugin(self, plugin_name, sync=False):
         try:
@@ -282,6 +328,7 @@ class Senpy(object):
         else:
             th = Thread(target=deact)
             th.start()
+            return th
 
     @classmethod
     def validate_info(cls, info):
@@ -295,13 +342,19 @@ class Senpy(object):
     def _install_deps(cls, info=None):
         requirements = info.get('requirements', [])
         if requirements:
-            pip_args = []
+            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))
-            pip.main(pip_args)
+            process = subprocess.Popen(pip_args,
+                                       stdout=subprocess.PIPE,
+                                       stderr=subprocess.PIPE)
+            log_subprocess_output(process)
+            exitcode = process.wait()
+            if exitcode != 0:
+                raise Error("Dependencies not properly installed")
 
     @classmethod
     def _load_module(cls, name, root):
@@ -366,23 +419,9 @@ class Senpy(object):
         return self._plugin_list
 
     def filter_plugins(self, **kwargs):
-        """ Filter plugins by different criteria """
+        return plugins.pfilter(self.plugins, **kwargs)
 
-        def matches(plug):
+    @property
-            res = all(getattr(plug, k, None) == v for (k, v) in kwargs.items())
+    def analysis_plugins(self):
-            logger.debug(
+        """ Return only the analysis plugins """
-                "matching {} with {}: {}".format(plug.name, kwargs, res))
+        return self.filter_plugins(plugin_type='analysisPlugin')
-            return res
-
-        if not kwargs:
-            return self.plugins
-        else:
-            return {n: p for n, p in self.plugins.items() if matches(p)}
-
-    def sentiment_plugins(self):
-        """ Return only the sentiment plugins """
-        return {
-            p: plugin
-            for p, plugin in self.plugins.items()
-            if isinstance(plugin, SentimentPlugin)
-        }

senpy/models.py

@@ -214,6 +214,7 @@ 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):
@@ -236,7 +237,10 @@ class BaseModel(SenpyMixin, dict):
         self.__setitem__(self._get_key(key), value)
 
     def __delattr__(self, key):
-        self.__delitem__(self._get_key(key))
+        try:
+            object.__delattr__(self, key)
+        except AttributeError:
+            self.__delitem__(self._get_key(key))
 
     def _plain_dict(self):
         d = {k: v for (k, v) in self.items() if k[0] != "_"}
@@ -252,13 +256,32 @@ def register(rsubclass, rtype=None):
     _subtypes[rtype or rsubclass.__name__] = rsubclass
 
 
-def from_dict(indict):
+def from_dict(indict, cls=None):
-    target = indict.get('@type', None)
+    if not cls:
-    if target and target in _subtypes:
+        target = indict.get('@type', None)
-        cls = _subtypes[target]
+        try:
-    else:
+            if target and target in _subtypes:
-        cls = BaseModel
+                cls = _subtypes[target]
-    return cls(**indict)
+            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_json(injson):
@@ -308,7 +331,7 @@ for i in [
 _ErrorModel = from_schema('error')
 
 
-class Error(SenpyMixin, BaseException):
+class Error(SenpyMixin, Exception):
     def __init__(self, message, *args, **kwargs):
         super(Error, self).__init__(self, message, message)
         self._error = _ErrorModel(message=message, *args, **kwargs)
@@ -337,5 +360,8 @@ class Error(SenpyMixin, BaseException):
     def __delattr__(self, key):
         delattr(self._error, key)
 
+    def __str__(self):
+        return str(self.to_JSON(with_context=False))
+
 
 register(Error, 'error')

senpy/plugins/__init__.py

@@ -9,11 +9,12 @@ import logging
 import tempfile
 import copy
 from .. import models
+from ..api import API_PARAMS
 
 logger = logging.getLogger(__name__)
 
 
-class SenpyPlugin(models.Plugin):
+class Plugin(models.Plugin):
     def __init__(self, info=None):
         """
         Provides a canonical name for plugins and serves as base for other
@@ -24,12 +25,24 @@ class SenpyPlugin(models.Plugin):
                                         "information for the plugin."))
         logger.debug("Initialising {}".format(info))
         id = 'plugins/{}_{}'.format(info['name'], info['version'])
-        super(SenpyPlugin, self).__init__(id=id, **info)
+        super(Plugin, self).__init__(id=id, **info)
         self.is_activated = False
 
     def get_folder(self):
         return os.path.dirname(inspect.getfile(self.__class__))
 
+    def activate(self):
+        pass
+
+    def deactivate(self):
+        pass
+
+
+SenpyPlugin = Plugin
+
+
+class AnalysisPlugin(Plugin):
+
     def analyse(self, *args, **kwargs):
         raise NotImplemented(
             'Your method should implement either analyse or analyse_entry')
@@ -48,30 +61,33 @@ class SenpyPlugin(models.Plugin):
         for i in results.entries:
             yield i
 
-    def activate(self):
+    def analyse_entries(self, entries, parameters):
-        pass
+        for entry in entries:
-
+            logger.debug('Analysing entry with plugin {}: {}'.format(self, entry))
-    def deactivate(self):
+            for result in self.analyse_entry(entry, parameters):
-        pass
+                yield result
 
 
-class SentimentPlugin(models.SentimentPlugin, SenpyPlugin):
+class ConversionPlugin(Plugin):
+    pass
+
+
+class SentimentPlugin(models.SentimentPlugin, AnalysisPlugin):
     def __init__(self, info, *args, **kwargs):
         super(SentimentPlugin, self).__init__(info, *args, **kwargs)
         self.minPolarityValue = float(info.get("minPolarityValue", 0))
         self.maxPolarityValue = float(info.get("maxPolarityValue", 1))
 
 
-class EmotionPlugin(models.EmotionPlugin, SenpyPlugin):
+class EmotionPlugin(models.EmotionPlugin, AnalysisPlugin):
     def __init__(self, info, *args, **kwargs):
         super(EmotionPlugin, self).__init__(info, *args, **kwargs)
         self.minEmotionValue = float(info.get("minEmotionValue", -1))
         self.maxEmotionValue = float(info.get("maxEmotionValue", 1))
 
 
-class EmotionConversionPlugin(models.EmotionConversionPlugin, SenpyPlugin):
+class EmotionConversionPlugin(models.EmotionConversionPlugin, ConversionPlugin):
-    def __init__(self, info, *args, **kwargs):
+    pass
-        super(EmotionConversionPlugin, self).__init__(info, *args, **kwargs)
 
 
 class ShelfMixin(object):
@@ -80,7 +96,12 @@ class ShelfMixin(object):
         if not hasattr(self, '_sh') or self._sh is None:
             self.__dict__['_sh'] = {}
             if os.path.isfile(self.shelf_file):
-                self.__dict__['_sh'] = pickle.load(open(self.shelf_file, 'rb'))
+                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
         return self._sh
 
     @sh.deleter
@@ -102,3 +123,40 @@ 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}

senpy/plugins/conversion/centroids.py

@@ -1,52 +0,0 @@
-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].iteritems():
-                    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

senpy/plugins/conversion/emotion/centroids.py

@@ -0,0 +1,102 @@
+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

senpy/plugins/conversion/emotion/ekman2fsre.senpy

@@ -0,0 +1,39 @@
+---
+name: Ekman2FSRE
+module: senpy.plugins.conversion.emotion.centroids
+description: Plugin to convert emotion sets from Ekman to VAD
+version: 0.1
+# No need to specify onyx:doesConversion because centroids.py adds it automatically from centroids_direction
+centroids:
+  anger:
+    A: 6.95
+    D: 5.1
+    V: 2.7
+  disgust:
+    A: 5.3
+    D: 8.05
+    V: 2.7
+  fear:
+    A: 6.5
+    D: 3.6
+    V: 3.2
+  happiness:
+    A: 7.22
+    D: 6.28
+    V: 8.6
+  sadness:
+    A: 5.21
+    D: 2.82
+    V: 2.21
+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:arousal
+  V: emoml:valence
+  D: emoml:dominance
+  anger: emoml:big6anger
+  disgust: emoml:big6disgust
+  fear: emoml:big6fear
+  happiness: emoml:big6happiness
+  sadness: emoml:big6sadness

senpy/plugins/conversion/emotion/ekman2vad.senpy

@@ -1,38 +1,44 @@
 ---
-name: Ekman2VAD
+name: Ekman2PAD
-module: senpy.plugins.conversion.centroids
+module: senpy.plugins.conversion.emotion.centroids
 description: Plugin to convert emotion sets from Ekman to VAD
 version: 0.1
-onyx:doesConversion:
+# No need to specify onyx:doesConversion because centroids.py adds it automatically from centroids_direction
-  - onyx:conversionFrom: emoml:big6
+origin:
-    onyx:conversionTo: emoml:fsre-dimensions
+  # Point in VAD space with no emotion (aka Neutral)
-  - onyx:conversionFrom: emoml:fsre-dimensions
+  A: 5.0
-    onyx:conversionTo: emoml:big6
+  D: 5.0
+  V: 5.0
 centroids:
-  emoml:big6anger:
+  anger:
     A: 6.95
     D: 5.1
     V: 2.7
-  emoml:big6disgust:
+  disgust:
     A: 5.3
     D: 8.05
     V: 2.7
-  emoml:big6fear:
+  fear:
     A: 6.5
     D: 3.6
     V: 3.2
-  emoml:big6happiness:
+  happiness:
     A: 7.22
     D: 6.28
     V: 8.6
-  emoml:big6sadness:
+  sadness:
     A: 5.21
     D: 2.82
     V: 2.21
 centroids_direction:
   - emoml:big6
-  - emoml:fsre-dimensions
+  - emoml:pad
-aliases:
+aliases: # These are aliases for any key in the centroid, to avoid repeating a long name several times
   A: emoml:arousal
   V: emoml:valence
-  D: emoml:dominance
+  D: emoml:dominance
+  anger: emoml:big6anger
+  disgust: emoml:big6disgust
+  fear: emoml:big6fear
+  happiness: emoml:big6happiness
+  sadness: emoml:big6sadness

senpy/plugins/split/split.py

@@ -0,0 +1,30 @@
+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_id = entry.id
+        original_text = entry.get("text", None)
+        if chunker_type == "sentence":
+            tokenizer = PunktSentenceTokenizer()
+            chars = tokenizer.span_tokenize(original_text)
+            for i, sentence in enumerate(tokenizer.tokenize(original_text)):
+                e = Entry()
+                e.text = sentence
+                e.id = original_id + "#char={},{}".format(chars[i][0], chars[i][1])
+                yield e
+        if chunker_type == "paragraph":
+            tokenizer = LineTokenizer()
+            chars = tokenizer.span_tokenize(original_text)
+            for i, paragraph in enumerate(tokenizer.tokenize(original_text)):
+                e = Entry() 
+                e.text = paragraph
+                chars = [char for char in chars]
+                e.id = original_id + "#char={},{}".format(chars[i][0], chars[i][1])
+                yield e

senpy/plugins/split/split.senpy

@@ -0,0 +1,18 @@
+---
+name: split
+module: split
+description: A sample plugin that chunks input text
+author: "@militarpancho"
+version: '0.1'
+url: "https://github.com/gsi-upm/senpy"
+requirements: {nltk}
+extra_params:
+  delimiter:
+    aliases:
+    - type
+    - t
+    required: false
+    default: sentence
+    options:
+    - sentence
+    - paragraph

senpy/schemas/context.jsonld

@@ -37,6 +37,12 @@
       "@type": "@id",
       "@container": "@set"
     },
+    "options": {
+      "@container": "@set"
+    },
+    "plugins": {
+      "@container": "@set"
+    },
     "prov:wasGeneratedBy": {
       "@type": "@id"
     },

senpy/schemas/plugins.json

@@ -6,11 +6,10 @@
       "properties": {
         "plugins": {
           "type": "array",
+          "default": [],
           "items": {
             "$ref": "plugin.json"
           }
-        },
-        "@type": {
         }
       }
     }

senpy/schemas/results.json

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

senpy/templates/index.html

@@ -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, which should be <a href="/api">here</a>.
+                    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.
                   </p>
                   <p>
                     These are some of the things you can do with the API:

senpy/version.py

@@ -8,8 +8,12 @@ DEFAULT_FILE = os.path.join(ROOT, 'VERSION')
 
 
 def read_version(versionfile=DEFAULT_FILE):
-    with open(versionfile) as f:
+    try:
-        return f.read().strip()
+        with open(versionfile) as f:
+            return f.read().strip()
+    except IOError:  # pragma: no cover
+        logger.error('Running an unknown version of senpy. Be careful!.')
+        return '0.0'
 
 
 __version__ = read_version()

setup.cfg

@@ -11,4 +11,7 @@ max-line-length = 100
 [bdist_wheel]
 universal=1
 [tool:pytest]
-addopts = --cov=senpy --cov-report term-missing
+addopts = --cov=senpy --cov-report term-missing
+
+[coverage:report]
+omit = senpy/__main__.py

tests/plugins/async_plugin/asyncplugin.py

@@ -0,0 +1,23 @@
+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

tests/plugins/async_plugin/asyncplugin.senpy

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

tests/plugins/dummy_plugin/dummy.py

@@ -4,4 +4,5 @@ from senpy.plugins import SentimentPlugin
 class DummyPlugin(SentimentPlugin):
     def analyse_entry(self, entry, params):
         entry.text = entry.text[::-1]
+        entry.reversed = entry.get('reversed', 0) + 1
         yield entry

tests/plugins/sleep_plugin/sleep.py

@@ -1,8 +1,8 @@
-from senpy.plugins import SenpyPlugin
+from senpy.plugins import AnalysisPlugin
 from time import sleep
 
 
-class SleepPlugin(SenpyPlugin):
+class SleepPlugin(AnalysisPlugin):
     def activate(self, *args, **kwargs):
         sleep(self.timeout)
 

tests/test_blueprints.py

@@ -19,6 +19,7 @@ def parse_resp(resp):
 class BlueprintsTest(TestCase):
     def setUp(self):
         self.app = Flask("test_extensions")
+        self.app.debug = False
         self.client = self.app.test_client()
         self.senpy = Senpy()
         self.senpy.init_app(self.app)

tests/test_client.py

@@ -4,18 +4,21 @@ try:
 except ImportError:
     from mock import patch
 
+import json
+
 from senpy.client import Client
-from senpy.models import Results, Error
+from senpy.models import Results, Plugins, Error
+from senpy.plugins import AnalysisPlugin, default_plugin_type
 
 
 class Call(dict):
     def __init__(self, obj):
-        self.obj = obj.jsonld()
+        self.obj = obj.serialize()
         self.status_code = 200
         self.content = self.json()
 
     def json(self):
-        return self.obj
+        return json.loads(self.obj)
 
 
 class ModelsTest(TestCase):
@@ -44,3 +47,19 @@ 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})

tests/test_extensions.py

@@ -10,7 +10,7 @@ except ImportError:
 
 from functools import partial
 from senpy.extensions import Senpy
-from senpy.models import Error, Results, Entry, EmotionSet, Emotion
+from senpy.models import Error, Results, Entry, EmotionSet, Emotion, Plugin
 from flask import Flask
 from unittest import TestCase
 
@@ -61,6 +61,19 @@ class ExtensionsTest(TestCase):
         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
+        }
+        root = os.path.join(self.dir, 'plugins', 'dummy_plugin')
+        with self.assertRaises(Error):
+            name, module = self.senpy._load_plugin_from_info(info, root=root)
+
     def test_disabling(self):
         """ Disabling a plugin """
         self.senpy.deactivate_all(sync=True)
@@ -96,19 +109,49 @@ class ExtensionsTest(TestCase):
         assert r2.analysis[0] == "plugins/Dummy_0.1"
         assert r1.entries[0].text == 'input'
 
+    def test_analyse_jsonld(self):
+        """ Using a plugin with JSON-LD input"""
+        js_input = '''{
+        "@id": "prueba",
+        "@type": "results",
+        "entries": [
+          {"@id": "entry1",
+           "text": "tupni",
+           "@type": "entry"
+          }
+        ]
+        }'''
+        r1 = self.senpy.analyse(algorithm="Dummy",
+                                input=js_input,
+                                informat="json-ld",
+                                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].text == 'input'
+
     def test_analyse_error(self):
         mm = mock.MagicMock()
-        mm.analyse_entry.side_effect = Error('error on analysis', status=900)
+        mm.id = 'magic_mock'
+        mm.analyse_entries.side_effect = Error('error on analysis', status=500)
         self.senpy.plugins['MOCK'] = mm
-        resp = self.senpy.analyse(input='nothing', algorithm='MOCK')
+        try:
-        assert resp['message'] == 'error on analysis'
+            self.senpy.analyse(input='nothing', algorithm='MOCK')
-        assert resp['status'] == 900
+            assert False
+        except Error as ex:
+            assert ex['message'] == 'error on analysis'
+            assert ex['status'] == 500
+
         mm.analyse.side_effect = Exception('generic exception on analysis')
-        mm.analyse_entry.side_effect = Exception(
+        mm.analyse_entries.side_effect = Exception(
             'generic exception on analysis')
-        resp = self.senpy.analyse(input='nothing', algorithm='MOCK')
+
-        assert resp['message'] == 'generic exception on analysis'
+        try:
-        assert resp['status'] == 500
+            self.senpy.analyse(input='nothing', algorithm='MOCK')
+            assert False
+        except Error as ex:
+            assert ex['message'] == 'generic exception on analysis'
+            assert ex['status'] == 500
 
     def test_filtering(self):
         """ Filtering plugins """
@@ -124,12 +167,13 @@ class ExtensionsTest(TestCase):
         assert len(senpy.plugins) > 1
 
     def test_convert_emotions(self):
-        self.senpy.activate_all()
+        self.senpy.activate_all(sync=True)
-        plugin = {
+        plugin = 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,
@@ -145,19 +189,31 @@ class ExtensionsTest(TestCase):
                   'conversion': 'full'}
         r1 = deepcopy(response)
         self.senpy.convert_emotions(r1,
-                                    plugin,
+                                    [plugin, ],
                                     params)
         assert len(r1.entries[0].emotions) == 2
         params['conversion'] = 'nested'
         r2 = deepcopy(response)
         self.senpy.convert_emotions(r2,
-                                    plugin,
+                                    [plugin, ],
                                     params)
         assert len(r2.entries[0].emotions) == 1
         assert r2.entries[0].emotions[0]['prov:wasDerivedFrom'] == eSet1
         params['conversion'] = 'filtered'
         r3 = deepcopy(response)
         self.senpy.convert_emotions(r3,
-                                    plugin,
+                                    [plugin, ],
                                     params)
         assert len(r3.entries[0].emotions) == 1
+        r3.jsonld()
+
+    # def test_async_plugin(self):
+    #     """ We should accept multiprocessing plugins with async=False"""
+    #     thread1 = self.senpy.activate_plugin("Async", sync=False)
+    #     thread1.join(timeout=1)
+    #     assert len(self.senpy.plugins['Async'].value) == 4
+
+    #     resp = self.senpy.analyse(input='nothing', algorithm='Async')
+
+    #     assert len(resp.entries[0].async_values) == 2
+    #     self.senpy.activate_plugin("Async", sync=True)

tests/test_models.py

@@ -11,8 +11,12 @@ from senpy.models import (Emotion,
                           Entry,
                           Error,
                           Results,
-                          Sentiment)
+                          Sentiment,
-from senpy.plugins import SenpyPlugin
+                          Plugins,
+                          Plugin,
+                          from_string,
+                          from_dict)
+from senpy import plugins
 from pprint import pprint
 
 
@@ -53,8 +57,8 @@ 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
@@ -94,20 +98,32 @@ class ModelsTest(TestCase):
         r.validate()
 
     def test_plugins(self):
-        self.assertRaises(Error, SenpyPlugin)
+        self.assertRaises(Error, plugins.Plugin)
-        p = SenpyPlugin({"name": "dummy", "version": 0})
+        p = plugins.Plugin({"name": "dummy",
+                            "version": 0,
+                            "extra_params": {
+                                "none": {
+                                    "options": ["es", ],
+                                    "required": False,
+                                    "default": "0"
+                                }
+                            }})
         c = p.jsonld()
-        assert "info" not in c
+        assert '@type' in c
-        assert "repo" not in c
+        assert c['@type'] == 'plugin'
-        assert "extra_params" in c
+        assert 'info' not in c
-        logging.debug("Framed:")
+        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 = SenpyPlugin({"name": "STR test", "version": 0})
+        p = plugins.Plugin({"name": "STR test", "version": 0})
         p._testing = 0
         s = str(p)
         assert "_testing" not in s
@@ -143,3 +159,40 @@ 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',
+                'text': '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)

tests/test_plugins.py

@@ -6,8 +6,9 @@ import shutil
 import tempfile
 
 from unittest import TestCase
-from senpy.models import Results, Entry
+from senpy.models import Results, Entry, EmotionSet, Emotion
 from senpy.plugins import SentimentPlugin, ShelfMixin
+from senpy.plugins.conversion.emotion.centroids import CentroidConversion
 
 
 class ShelfDummyPlugin(SentimentPlugin, ShelfMixin):
@@ -83,7 +84,39 @@ class PluginsTest(TestCase):
         res2 = a.analyse(input=1)
         assert res2.entries[0].nif__isString == 2
 
-    def test_two(self):
+    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):
         ''' Reusing the values of a previous shelf '''
         a = ShelfDummyPlugin(info={
             'name': 'shelve',
@@ -120,3 +153,52 @@ 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)
+
+        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"