added initial docs

README.md

@@ -6,6 +6,9 @@ Languages.jl
 [![pkgeval](https://juliahub.com/docs/Languages/pkgeval.svg)](https://juliahub.com/ui/Packages/Languages/w1H1r)
 
 
+[![](https://img.shields.io/badge/docs-stable-blue.svg)](https://juliatext.github.io/Languages.jl) [![](https://img.shields.io/badge/docs-dev-blue.svg)](https://juliatext.github.io/Languages.jl/dev)
+
+
 ## Introduction
 
 Languages.jl is a Julia package for working with human languages. It provides:

docs/.gitignore

@@ -0,0 +1,2 @@
+build/
+site/

docs/Project.toml

@@ -0,0 +1,2 @@
+[deps]
+Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"

docs/make.jl

@@ -0,0 +1,16 @@
+using Documenter
+using Languages
+
+makedocs(
+    sitename = "Languages",
+    format = Documenter.HTML(),
+    modules = [Languages],
+    pages = [
+        "Home" => "index.md",
+        "API" => "api.md"
+    ]
+)
+
+deploydocs(
+    repo = "github.com/JuliaText/Languages.jl.git"
+)

docs/src/api.md

@@ -0,0 +1,4 @@
+```@autodocs
+Modules = [Languages]
+Private = false
+```

docs/src/index.md

@@ -0,0 +1,57 @@
+# Languages.jl
+
+Languages.jl is a Julia package for working with human languages. It provides:
+
+* Lists of words from each language for basic categories:
+	* Articles
+		* Indefinite Articles
+		* Definite Articles
+	* Prepositions
+	* Pronouns
+	* Stopwords
+
+	These methods are supported only for English and German currently.
+
+	This package also detects the script and language for written text in a wide variety of languages.  
+
+## Usage
+
+	using Languages
+
+	articles(Languages.English())
+	stopwords(Languages.English())
+
+All word lists are returned as vectors of UTF-8 strings.
+
+## Script detection
+
+Script detection model works by checking the unicode character ranges present within
+the input text
+
+  Languages.detect_script("To be or not to be") # => Languages.LatinScript()
+
+## Language Detection
+
+A trigram based model is used to detect the language for the text. The model is
+filtered based on the detected script.
+
+We detect 84 of the most common languages spoken around the world. This usually
+covers most languages with more than 10 million native speakers.
+
+  detector = LanguageDetector()
+  detector("To be or not to be") #=>  (Languages.English(), Languages.LatinScript(), 1.0)
+
+## List All Supported Languages
+You can use `list_languages()` to get all supported languages.
+
+The `LanguageDetector` model returns the language, the script, and the confidence when applied to a string.
+
+The language and script detection code in this package is heavily inspired from  the rust package [whatlang-rs](https://github.com/greyblake/whatlang-rs). That package is in turn derived from [franc](https://github.com/wooorm/franc). See `LICENSE.whatlang-rs` for details.
+
+## Deprecations
+
+The API of this package has been refurbished recently. If you have used this package earlier,
+please be aware of these changes.
+
+  * The language names have been shortened. So `English` instead of `EnglishLanguage`. However, the language names are no longer exported. So they should be referred to with the package name: `Languages.English`
+  * Every language is a type. However all functions now accept and return instances of these types, rather than the types themselves.

src/types.jl

@@ -5,8 +5,25 @@ abstract type Language; end
 # Portuguese, Romanian, Russian, Spanish, Swedish, Turkish
 
 # These are ISO 639-2T alpha-3 and ISO 639-3 codes
+"""
+    isocode(lang::T) where {T<:Language}
+
+Returns ISO code of the `lang`
+"""
 isocode(lang::T) where {T<:Language} = isocode(T)
+
+"""
+    name(lang::T) where {T<:Language}
+
+Returns the self-name of the language `lang`.
+"""
 name(lang::T) where {T<:Language} = name(T)
+
+"""
+    english_name(lang::T) where {T<:Language}
+
+Returns the name of the language `lang` in English.
+"""
 english_name(lang::T) where {T<:Language} = english_name(T)
 
 struct Esperanto <: Language; end;	english_name(::Type{Esperanto}) = "Esperanto";	name(::Type{Esperanto}) = "Esperanto";	isocode(::Type{Esperanto}) = "epo";
@@ -182,6 +199,11 @@ global const code_to_lang = Dict{String, Language}(
     "uig"  => Uyghur(),
     )
 
+"""
+    from_code(code::String)
+
+Returns the language object for the ISO `code`.
+"""
 function from_code(code::String)
     return get(code_to_lang, lowercase(code), nothing)
 end

src/whatlang.jl

@@ -9,6 +9,12 @@
 
 const RELIABLE_CONFIDENCE_THRESHOLD = 0.8;
 
+"""
+    detect_script(text::AbstractString)
+
+Detect a script for the given `text`.
+Returns either `Script` or a tuple `(Script, probability)`.
+"""
 function detect_script(text::AbstractString)
     script_counters = [
       [LatinScript()      , 0],
@@ -384,6 +390,11 @@ Base.@deprecate detect(text::AbstractString, options=default_options()) Language
 mutable struct LanguageDetector
 end
 
+"""
+    detector::LanguageDetector(text::AbstractString, options=default_options())
+
+Returns a tuple `(Language, Script, confidence)` for the given `text`
+"""
 function(m::LanguageDetector)(text::AbstractString, options=default_options())
     if text==""; throw(ArgumentError("Cannot detect language for empty text")); end
     script = detect_script(text)