From df51f8af0743a333115244fa33ca4a2c4527dce3 Mon Sep 17 00:00:00 2001
From: Josh Devins <josh.devins@elastic.co>
Date: Thu, 28 Oct 2021 19:05:39 +0200
Subject: [PATCH] Document how to install transitive binary dependencies, add
 repo Dockerfile

Co-authored-by: Seth Michael Larson <seth.larson@elastic.co>
---
 Dockerfile | 14 ++++++++++++++
 README.md  | 53 +++++++++++++++++++++++++++++++++++++++++++++++------
 setup.py   | 24 +++++++++++++-----------
 3 files changed, 74 insertions(+), 17 deletions(-)
 create mode 100644 Dockerfile

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..75ab72d
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,14 @@
+FROM debian:11.1
+
+RUN apt-get update && \
+    apt-get install -y build-essential pkg-config cmake \
+                       python3-dev python3-pip python3-venv \
+                       libzip-dev libjpeg-dev && \
+    apt-get clean
+
+ADD . /eland
+WORKDIR /eland
+
+RUN python3 -m pip install --no-cache-dir --disable-pip-version-check .[all]
+
+CMD ["/bin/sh"]
diff --git a/README.md b/README.md
index 0bde260..4c21f7d 100644
--- a/README.md
+++ b/README.md
@@ -22,16 +22,16 @@
 
 ## About
 
-Eland is a Python Elasticsearch client for exploring and
-analyzing data in Elasticsearch with a familiar Pandas-compatible API.
+Eland is a Python Elasticsearch client for exploring and  analyzing data in Elasticsearch with a familiar
+Pandas-compatible API.
 
 Where possible the package uses existing Python APIs and data structures to make it easy to switch between numpy,
-pandas, scikit-learn to their Elasticsearch powered equivalents. In general, the data resides in Elasticsearch and
+pandas, or scikit-learn to their Elasticsearch powered equivalents. In general, the data resides in Elasticsearch and
 not in memory, which allows Eland to access large datasets stored in Elasticsearch.
 
-Eland also provides tools to upload trained machine learning models from your
-common libraries like [scikit-learn](https://scikit-learn.org), [XGBoost](https://xgboost.readthedocs.io),
-and [LightGBM](https://lightgbm.readthedocs.io) into Elasticsearch.
+Eland also provides tools to upload trained machine learning models from common libraries like
+[scikit-learn](https://scikit-learn.org), [XGBoost](https://xgboost.readthedocs.io),  and
+[LightGBM](https://lightgbm.readthedocs.io) into Elasticsearch.
 
 ## Getting Started
 
@@ -52,6 +52,47 @@ $ conda install -c conda-forge eland
 - Supports Python 3.7+ and Pandas 1.3
 - Supports Elasticsearch clusters that are 7.11+, recommended 7.14 or later for all features to work.
 
+### Prerequisites
+
+Users installing Eland on Debian-based distributions may need to install prerequisite packages for the transitive
+dependencies of Eland:
+
+```bash
+$ sudo apt-get install -y \
+  build-essential pkg-config cmake \
+  python3-dev libzip-dev libjpeg-dev
+```
+
+Note that other distributions such as CentOS, RedHat, Arch, etc. may require using a different package manager and
+specifying different package names. 
+
+### Docker
+
+Users wishing to use Eland without installing it, in order to just run the available scripts, can build the Docker
+container:
+
+```bash
+$ docker build -t elastic/eland .
+```
+
+The container can now be used interactively:
+
+```bash
+$ docker run -it --rm --network host elastic/eland
+```
+
+Running installed scripts is also possible without an interactive shell, e.g.:
+
+```bash
+$ docker run -it --rm --network host \
+    elastic/eland \
+    eland_import_hub_model \
+      --url http://host.docker.internal:9200/ \
+      --hub-model-id elastic/distilbert-base-cased-finetuned-conll03-english \
+      --task-type ner \
+      --start
+```
+
 ### Connecting to Elasticsearch 
 
 Eland uses the [Elasticsearch low level client](https://elasticsearch-py.readthedocs.io) to connect to Elasticsearch. 
diff --git a/setup.py b/setup.py
index b21d82a..4f0f2c5 100644
--- a/setup.py
+++ b/setup.py
@@ -54,6 +54,18 @@ with open(path.join(here, "README.md"), "r", "utf-8") as f:
             last_html_index = i + 1
     long_description = "\n".join(lines[last_html_index:])
 
+extras = {
+    "xgboost": ["xgboost>=0.90,<2"],
+    "scikit-learn": ["scikit-learn>=0.22.1,<1"],
+    "lightgbm": ["lightgbm>=2,<4"],
+    "pytorch": [
+        "huggingface-hub>=0.0.17,<1",
+        "sentence-transformers>=2.0.0,<3",
+        "torch>=1.9.0,<2",
+        "transformers[torch]>=4.11.0<5",
+    ],
+}
+extras["all"] = list({dep for deps in extras.values() for dep in deps})
 
 setup(
     name=about["__title__"],
@@ -81,15 +93,5 @@ setup(
     package_data={"eland": ["py.typed"]},
     include_package_data=True,
     zip_safe=False,
-    extras_require={
-        "xgboost": ["xgboost>=0.90,<2"],
-        "scikit-learn": ["scikit-learn>=0.22.1,<1"],
-        "lightgbm": ["lightgbm>=2,<4"],
-        "pytorch": [
-            "huggingface-hub>=0.0.17,<1",
-            "sentence-transformers>=2.0.0,<3",
-            "torch>=1.9.0,<2",
-            "transformers[torch]>=4.11.0<5",
-        ],
-    },
+    extras_require=extras,
 )