Corpus Module Cleanup

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/conf.py

@@ -0,0 +1,54 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# http://www.sphinx-doc.org/en/master/config
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+
+# -- Project information -----------------------------------------------------
+
+project = 'Iranlowo'
+copyright = '2019, Ruoho Ruosi , Olamilekan Wahab'
+author = 'Ruoho Ruosi , Olamilekan Wahab'
+
+# The full version, including alpha/beta/rc tags
+release = '0.1'
+
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = ['recommonmark']
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'alabaster'
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']

docs/index.rst

@@ -0,0 +1,10 @@
+.. Iranlowo documentation master file, created by
+   sphinx-quickstart on Sat Jul  6 09:15:49 2019.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+.. include:: ../README.rst
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Contents:

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

requirements.txt

@@ -1,3 +1,4 @@
+PyYAML
 bs4
 configargparse
 torch

src/iranlowo/corpus/__init__.py

@@ -1,2 +1,7 @@
-from .corpus import Corpus, DirectoryCorpus
-from .loaders import OweLoader, YorubaBlogCorpus, BBCCorpus, BibeliCorpus
+from .corpus import (
+    Corpus,
+    DirectoryCorpus,
+    get_corpus,
+    get_corpus_path,
+    download_corpus,
+)

src/iranlowo/corpus/corpus.py

@@ -1,6 +1,7 @@
 import gzip
 import os
 
+import yaml
 from gensim import interfaces
 from gensim.corpora.csvcorpus import CsvCorpus
 from gensim.corpora.textcorpus import walk
@@ -10,7 +11,16 @@
 
 
 class Corpus(interfaces.CorpusABC):
-    def __init__(self, path=None, text=None, stream=False, fformat='txt', cformat=None, labels=False, preprocess=None):
+    def __init__(
+        self,
+        path=None,
+        text=None,
+        stream=False,
+        fformat="txt",
+        cformat=None,
+        labels=False,
+        preprocess=None,
+    ):
         """
 
         Args:
@@ -24,10 +34,16 @@ def __init__(self, path=None, text=None, stream=False, fformat='txt', cformat=No
         self.fformat = fformat
         self.cformat = cformat
         self.preprocess = preprocess
-        assert self.path or self.text, "You should pass either a path or text to read data from."
+        assert (
+            self.path or self.text
+        ), "You should pass either a path or text to read data from."
         if not self.preprocess:
             self.preprocess = [normalize_diacritics_text]
-        self.data = self.read_file_filename_or_text(text=text) if text else self.read_file_filename_or_text()
+        self.data = (
+            self.read_file_filename_or_text(text=text)
+            if text
+            else self.read_file_filename_or_text()
+        )
         self.validate_format()
 
     def __iter__(self):
@@ -69,12 +85,14 @@ def read_file_filename_or_text(self, f=None, text=None):
                     text = open(path)
                 elif self.fformat == "csv":
                     text = CsvCorpus(path, self.labels)
-                elif self.fformat == 'gzip':
+                elif self.fformat == "gzip":
                     text = gzip.open(path)
             else:
                 text = self.path.seek(0)
 
-            text = text.read() if not self.stream else ''.join(list(self.streamfile(text)))
+            text = (
+                text.read() if not self.stream else "".join(list(self.streamfile(text)))
+            )
             return self.handle_preprocessing(text) if self.preprocess else text
 
     def handle_preprocessing(self, text):
@@ -93,12 +111,16 @@ def validate_format(self):
         """
         data = self.data
         if isinstance(data, list):
-            data = ''.join(data)
+            data = "".join(data)
         if not self.cformat and not is_text_nfc(data):
             raise TypeError("The corpus does not comply to the NFC corpus format")
         elif self.cformat == "owe":
             if not is_valid_owé_format(data):
-                raise TypeError("The corpus does not comply to the {0} corpus format".format(self.cformat))
+                raise TypeError(
+                    "The corpus does not comply to the {0} corpus format".format(
+                        self.cformat
+                    )
+                )
             else:
                 return True
 
@@ -118,15 +140,56 @@ def generate(self, size):
 class DirectoryCorpus(Corpus):
     def __init__(self, path, **kwargs):
         self.dir_path = path
-        self.depth = kwargs.get('min_depth', 0)
+        self.depth = kwargs.get("min_depth", 0)
         self.path = list(self.read_files())
         super(DirectoryCorpus, self).__init__(path=self.path, **kwargs)
 
     def read_files(self):
         walked = list(walk(self.dir_path))
         if not walked:
-            raise NotADirectoryError("'{}' is not a valid directory".format(self.dir_path))
+            raise NotADirectoryError(
+                "'{}' is not a valid directory".format(self.dir_path)
+            )
         for depth, dirpath, _, filenames in walked:
             if self.depth <= depth:
                 for path in filenames:
                     yield os.path.join(dirpath, path)
+
+
+def get_corpus(name, niger_volta=False, **kwargs):
+    def file_or_dir(path, mode):
+        if mode == "single":
+            return Corpus(path=path, **kwargs)
+        else:
+            return DirectoryCorpus(path=path, **kwargs)
+
+    with open(os.path.join(os.path.dirname(__file__), "corpus.yml"), "r") as stream:
+        data = yaml.safe_load(stream)
+    if niger_volta:
+        nvc = data.get("niger_volta")
+        if name not in nvc.keys():
+            raise ValueError("Corpus {} does not exist".format(name))
+        else:
+            if not os.environ.get("NIGER_VOLTA_CORPUS", None):
+                raise NotADirectoryError(
+                    "NIGER_VOLTA_CORPUS environment variable not found. Please, clone the corpus repository from https://github.com/Niger-Volta-LTI/yoruba-text and set to NIGER_VOLTA_CORPUS to it's "
+                    "path"
+                )
+            path = os.path.join(os.environ["NIGER_VOLTA_CORPUS"], nvc[name]["path"])
+            return file_or_dir(path, nvc[name]["mode"])
+    else:
+        path = os.path.join(os.path.dirname(__file__), "corpus/{}".format(data["path"]))
+        return file_or_dir(path, data["mode"])
+
+
+def get_corpus_path(name):
+    with open(os.path.join(os.path.dirname(__file__), "corpus.yml"), "r") as stream:
+        data = yaml.safe_load(stream)
+        if name not in data.keys():
+            raise ValueError("Corpus {} does not exist".format(name))
+        else:
+            return os.path.join(os.path.dirname(__file__), data[name])
+
+
+def download_corpus(name, uri=None):
+    pass

src/iranlowo/corpus/corpus.yml

@@ -0,0 +1,13 @@
+niger_volta:
+      yoruba_blog:
+          path: "TheYorubaBlog/theyorubablog_dot_com.txt"
+          mode: single
+      owe_yoruba:
+          path: " "
+          mode: dir
+      quran_mimo:
+          path: " "
+          mode: dir
+      asubiaro:
+          path: " "
+          mode: single

src/iranlowo/corpus/loaders.py

@@ -1,66 +1,7 @@
 import os
 
-from iranlowo.corpus import Corpus, DirectoryCorpus
+from iranlowo.corpus import get_corpus
 
 
-class BaseLoader(object):
-    def __init__(self, corpus_path):
-        self.corpus_path = corpus_path
-        yoruba_text_path = os.environ.get("YORUBA_TEXT_PATH", None)
-        if not yoruba_text_path:
-            raise NotADirectoryError(
-                "YORUBA_TEXT_PATH environment variable not found. Please, clone the corpus repository from https://github.com/Niger-Volta-LTI/yoruba-text and set to YORUBA_TEXT_PATH to it's "
-                "path")
-        else:
-            corpus_path = "{}/{}".format(yoruba_text_path, corpus_path)
-            self.path = corpus_path
-
-
-class YorubaBlogCorpus(Corpus):
-    def __init__(self, path):
-        """
-
-        Args:
-            path:
-        """
-        super(YorubaBlogCorpus, self).__init__(path=self.path, **kwargs)
-
-
-class BBCCorpus(Corpus):
-    def __init__(self, path):
-        """
-
-        Args:
-            path:
-        """
-        super(BBCCorpus, self).__init__(path=self.path, **kwargs)
-        super().__init__(path)
-
-
-class BibeliCorpus(Corpus):
-    def __init__(self, path):
-        """
-
-        Args:
-            path:
-        """
-        super(BibeliCorpus, self).__init__(path=self.path, **kwargs)
-
-
-class en(BaseLoader, DirectoryCorpus):
-    def __init__(self):
-        BaseLoader.__init__(self, corpus_path="Owe/en")
-        DirectoryCorpus.__init__(self, path=self.path)
-
-
-class yo(BaseLoader, DirectoryCorpus):
-    def __init__(self):
-        BaseLoader.__init__(self, corpus_path="Owe/yo")
-        DirectoryCorpus.__init__(self, path=self.path)
-
-
-class OweLoader(object):
-    def __init__(self):
-        self.en = en()
-        self.yo = yo()
-
+def niger_volta_corpus(corpus_code):
+    return get_corpus(name=corpus_code, niger_volta=True)