From 6c8b32fad4cc9c6dca18e4183f1104b9981a8b9a Mon Sep 17 00:00:00 2001
From: Patrick Jentsch <pjentsch@pjentsch-Laptop.local>
Date: Mon, 20 May 2019 12:08:13 +0200
Subject: [PATCH] Update

---
 Dockerfile |  1 +
 README.md  | 86 ++++++++++++++++++++++++++++++++++++++----------------
 nlp        |  2 +-
 spacy_nlp  |  7 +++--
 4 files changed, 67 insertions(+), 29 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index b4ef535..7ba70b2 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -31,6 +31,7 @@ RUN pip3 install wheel && pip3 install -U spacy && \
     python3 -m spacy download en && \
     python3 -m spacy download es && \
     python3 -m spacy download fr && \
+    python3 -m spacy download it && \
     python3 -m spacy download pt
 
 COPY nlp /usr/local/bin
diff --git a/README.md b/README.md
index 856ae64..c11f4de 100644
--- a/README.md
+++ b/README.md
@@ -1,37 +1,73 @@
 # Natural language processing
 
-This repository provides all code that is needed to build a container image for natural language processing utilising [spaCy](https://spacy.io).
-In case you don't want to build the image by yourself, there is also a prebuild image that can be used in the [registry](https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp/container_registry).
+This repository provides all code that is needed to build a container image for natural language processing utilizing [spaCy](https://spacy.io).
 
-## Build the image
+## Build image
 
-```console
-user@machine:~$ cd <path-to-this-repository>
-user@machine:~$ docker build -t gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/nlp .
+1. Clone this repository and navigate into it:
+```
+git clone https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp.git && cd nlp
 ```
 
-## Starting a container
-
-```console
-user@machine:~$ docker run \
-  --name nlp-container \
-  -dit \
-  -v <your-input-directory>:/root/files_for_nlp \
-  -v <your-output-directory>:/root/files_from_nlp \
-  gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/nlp
+2. Build image:
+```
+docker build -t sfb1288inf/nlp:latest .
 ```
 
-## Start a natural language processing run
+Alternatively build from the GitLab repository without cloning:
 
-```console
-user@machine:~$ docker exec -it nlp-container \
-  nlp -i files_for_nlp -o files_from_nlp -l <language-code>
+1. Build image:
+```
+docker build -t sfb1288inf/nlp:latest https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp.git
 ```
 
-Where <language-code> needs to be one of the following:
+## Download prebuilt image
 
-* de (German)
-* en (English)
-* es (Spanish)
-* fr (French)
-* pt (Portuguese)
\ No newline at end of file
+The GitLab registry provides a prebuilt image. It is automatically created, utilizing the conquaire build servers.
+
+1. Download image:
+```
+docker pull gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/nlp:latest
+```
+
+## Run
+
+1. Create input and output directories for the NLP software:
+```
+mkdir -p /<mydatalocation>/files_for_nlp /<mydatalocation>/files_from_nlp
+```
+
+2. Place your text files inside the `/<mydatalocation>/files_for_nlp` directory. Files should all contain text of the same language.
+
+3. Start the NLP process.
+```
+docker run \
+    --rm \
+    -it \
+    -v /<mydatalocation>/files_for_nlp:/files_for_nlp \
+    -v /<mydatalocation>/files_from_nlp:/files_from_nlp \
+    sfb1288inf/nlp:latest \
+        -i /files_for_nlp \
+        -o /files_from_nlp \
+        -l <languagecode>
+```
+The arguments below `sfb1288inf/nlp:latest` are described in the [NLP arguments](#nlp-arguments) part.
+
+If you want to use the prebuilt image, replace `sfb1288inf/nlp:latest` with `gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/nlp:latest`.
+
+4. Check your results in the `/<mydatalocation>/files_from_nlp` directory.
+
+### NLP arguments
+
+`-i path`
+* Sets the input directory using the specified path.
+* required = True
+
+`-o path`
+* Sets the output directory using the specified path.
+* required = True
+
+`-l languagecode`
+* Tells spaCy which language will be used.
+* options = de (German), el (Greek), en (English), es (Spanish), fr (French), it (Italian), nl (Dutch), pt (Portuguese)
+* required = True
diff --git a/nlp b/nlp
index af92e18..203c922 100755
--- a/nlp
+++ b/nlp
@@ -28,7 +28,7 @@ def parse_arguments():
     )
     parser.add_argument(
         '-l',
-        choices=['de', 'en', 'es', 'fr', 'pt'],
+        choices=['de', 'el', 'en', 'es', 'fr', 'it', 'nl', 'pt'],
         dest='lang',
         required=True
     )
diff --git a/spacy_nlp b/spacy_nlp
index e01bb05..abf0fe9 100755
--- a/spacy_nlp
+++ b/spacy_nlp
@@ -15,7 +15,7 @@ parser.add_argument(
 )
 parser.add_argument(
     '-l',
-    choices=['de', 'en', 'es', 'fr', 'pt'],
+    choices=['de', 'el', 'en', 'es', 'fr', 'it', 'nl', 'pt'],
     dest='lang',
     required=True
 )
@@ -26,8 +26,9 @@ parser.add_argument(
 args = parser.parse_args()
 
 SPACY_MODELS = {
-    'de': 'de_core_news_sm', 'en': 'en_core_web_sm', 'es': 'es_core_news_sm',
-    'fr': 'fr_core_news_sm', 'pt': 'pt_core_news_sm'
+    'de': 'de_core_news_sm', 'el': 'el_core_news_sm', 'en': 'en_core_web_sm',
+    'es': 'es_core_news_sm', 'fr': 'fr_core_news_sm', 'it': 'it_core_news_sm',
+    'nl': 'nl_core_news_sm', 'pt': 'pt_core_news_sm'
 }
 
 # Set the language model for spacy