[RELEASE] The John Snow Labs Library 4.2.0

.gitignore

@@ -0,0 +1,332 @@
+.idea
+build
+dist
+nlu.egg-info
+.sass-cache
+personal_notes.md
+/tests/nlu_hc_tests/secrets.py
+/tests/nlu_hc_tests/spark_nlp_for_healthcare.json
+tmp
+# Created by https://www.gitignore.io/api/sbt,java,scala,python,eclipse,intellij,intellij+all
+
+### Eclipse ###
+
+.metadata
+bin/
+tmp/
+*.tmp
+*.bak
+*.swp
+*~.nib
+local.properties
+.settings/
+.loadpath
+.recommenders
+PubMed*
+*cache_pretrained*
+*.crc
+*.sst
+_SUCCESS*
+*stages*
+*auxdata*
+# External tool builders
+.externalToolBuilders/
+
+# Locally stored "Eclipse launch configurations"
+*.launch
+
+# PyDev specific (Python IDE for Eclipse)
+*.pydevproject
+
+# CDT-specific (C/C++ Development Tooling)
+.cproject
+
+# Java annotation processor (APT)
+.factorypath
+
+# PDT-specific (PHP Development Tools)
+.buildpath
+
+# sbteclipse plugin
+.target
+
+# Tern plugin
+.tern-project
+
+# TeXlipse plugin
+.texlipse
+
+# STS (Spring Tool Suite)
+.springBeans
+
+# Code Recommenders
+.recommenders/
+
+# Scala IDE specific (Scala & Java development for Eclipse)
+.cache-main
+.scala_dependencies
+.worksheet
+
+### Eclipse Patch ###
+# Eclipse Core
+.project
+
+# JDT-specific (Eclipse Java Development Tools)
+.classpath
+
+### Intellij ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and Webstorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff:
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/dictionaries
+
+# Sensitive or high-churn files:
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.xml
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+
+# Gradle:
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# CMake
+cmake-build-debug/
+
+# Mongo Explorer plugin:
+.idea/**/mongoSettings.xml
+
+## File-based project format:
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+/out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+### Intellij Patch ###
+# Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721
+
+*.iml
+# modules.xml
+# .idea/misc.xml
+# *.ipr
+
+# Sonarlint plugin
+.idea/sonarlint
+
+### Intellij+all ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and Webstorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff:
+
+# Sensitive or high-churn files:
+
+# Gradle:
+
+# CMake
+
+# Mongo Explorer plugin:
+
+## File-based project format:
+
+## Plugin-specific files:
+
+# IntelliJ
+
+# mpeltonen/sbt-idea plugin
+
+# JIRA plugin
+
+# Cursive Clojure plugin
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+
+### Intellij+all Patch ###
+# Ignores the whole idea jsl_folder
+# See https://github.com/joeblau/gitignore.io/issues/186 and https://github.com/joeblau/gitignore.io/issues/360
+
+.idea/
+
+### Java ###
+# Compiled class file
+*.class
+
+# Log file
+*.log
+
+# BlueJ files
+*.ctxt
+
+# Mobile Tools for Java (J2ME)
+.mtj.tmp/
+
+# Package Files #
+*.jar
+*.war
+*.ear
+*.zip
+*.tar.gz
+*.rar
+
+# virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml
+hs_err_pid*
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+python/lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+### SBT ###
+# Simple Build Tool
+# http://www.scala-sbt.org/release/docs/Getting-Started/Directories.html#configuring-version-control
+
+dist/*
+lib_managed/
+src_managed/
+project/boot/
+project/plugins/project/
+.history
+.lib/
+
+### Scala ###
+
+# End of https://www.gitignore.io/api/sbt,java,scala,python,eclipse,intellij,intellij+all
+
+### Local ###
+tmp_pipeline/
+tmp_symspell/
+test-output-tmp/
+spark-warehouse/
+/python/python.iml
+test_crf_pipeline/
+test_*_pipeline/
+*metastore_db*
+python/src/
+python/tensorflow/bert/models/**
+**/.DS_Store
+**/tmp_*
+docs/_site/**
+docs/.sass-cache/**
+
+tst_shortcut_sd/
+src/*/resources/*.classes

README.md

@@ -1,2 +1,4 @@
 # johnsnowlabs
-John Snow Labs NLP Library
+The John Snow Labs Library gives you access to all of John Snow Labs Enterprise And Open Source products in an easy and simple manner. Access 10000+ state-of-the-art NLP and OCR models for '
+'Finance, Legal and Medical domains. Easily scalable to Spark Cluster.
+See https://www.johnsnowlabs.com/  and [the docs](https://nlu.johnsnowlabs.com/docs/en/install) for more detials

johnsnowlabs/__init__.py

@@ -0,0 +1,17 @@
+from .auto_install.health_checks.report import check_health, list_remote_licenses, list_local_licenses
+from .utils.sparksession_utils import start
+from .auto_install.install_flow import install
+# get helpers into global space
+from johnsnowlabs import medical, nlp, ocr, settings, viz, finance, legal
+import johnsnowlabs as jsl
+
+# databricks
+from johnsnowlabs.auto_install.databricks.work_utils import run_in_databricks
+from johnsnowlabs.nlp import *
+
+
+def new_version_online():
+    from .utils.pip_utils import get_latest_lib_version_on_pypi
+    # we are outdated, if current version does not match the latest on PypPi
+    from .auto_install.softwares import Software
+    return settings.raw_version_jsl_lib != get_latest_lib_version_on_pypi(Software.jsl_lib.pypi_name)

johnsnowlabs/abstract_base/base_enum.py

@@ -0,0 +1,19 @@
+from enum import Enum, EnumMeta
+
+
+class MetaEnum(EnumMeta):
+
+    def __contains__(cls, item):
+        try:
+            cls(item)
+        except ValueError:
+            return False
+        return True
+
+    def from_name(cls, name):
+        return cls._member_map_[name]
+
+
+class BaseEnum(Enum, metaclass=MetaEnum):
+    # Enums extending this will support `in` keyword for values of enums
+    pass