textalyzer 0.2.0__py3-none-any.whl

textalyzer/Textalyzer.py

@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Jan 18 04:19:37 2017
+
+@author: lord
+"""
+
+import re
+
+from nltk.corpus import wordnet
+
+replacement_patterns = [
+    (r'isn\'t', 'is not'),
+    (r'won\'t', 'will not'),
+    (r'can\'t', 'cannot'),
+    (r'Can\'t', 'Can not'),
+    (r'don\'t', 'do not'),
+    (r'Don\'t', 'Do not'),
+    (r'it\'s', 'it is'),
+    (r'It\'s', 'It is'),
+    (r'shan\'t', 'shall not'),
+    (r'Shan\'t', 'Shall not'),
+    (r'i\'m', 'i am'),
+    (r'I\'m', 'I am'),
+    (r'ain\'t', 'is not'),
+    (r'Ain\'t', 'Is not'),
+    (r'you\'re', 'you are'),
+    (r'You\'re', 'You are'),
+    (r'aren\'t', 'Are not'),
+    (r'Aren\'t', 'Are not'),
+    (r'\\n\\n', '\n'),
+    (r'\\n', '\n'),
+    (r'\'', ''),
+    (r'\\r\n', '\n'),
+    (r'\\r', ''),
+    (r'/', ' '),
+    (r'\[', ''),
+    (r'\{', ''),
+    (r'\}', ''),
+    (r'\]', ''),
+    (r':', ''),
+    (r'data', ''),
+    (r'Anonymous', ''),
+    (r'(\w+)\'ll', '\g<1> will'),
+    (r'(\w+)n\'t', '\g<1> not'),
+    (r'(\w+)\'ve', '\g<1> have'),
+    (r'(\w+)\'s', '\g<1> is'),
+    (r'(\w+)\'re', '\g<1> are'),
+    (r'(\w+)\'r', '\g<1> are'),
+    (r'(\w+)\'d', '\g<1> would'),
+]
+
+# Class for replacing characters
+class ContractionReplacers(object):
+    def __init__(self, patterns=None):
+        if patterns is None:
+            patterns = replacement_patterns
+        patterns = list(patterns)
+        self.patterns = [(re.compile(regex, flags=re.I), repl) for (regex, repl) in patterns]
+
+    def text_replacers(self, text):
+        s = text
+        for (pattern, repl) in self.patterns:
+            (s, count) = re.subn(pattern, repl, s)
+        return s
+
+
+# Class for removing repeating characters
+class RepeatingReplacers(object):
+    def __init__(self, corpus=wordnet):
+        self.corpus = corpus
+        self.repeat_regexp = re.compile(r'(\w*)(\w)\2(\w*)')
+        self.repl = r'\1\2\3'
+
+    def text_repeaters(self, word):
+        if self.corpus.synsets(word):
+            return word
+        repl_word = self.repeat_regexp.sub(self.repl, word)
+        if repl_word != word:
+            return self.text_repeaters(repl_word)
+        else:
+            return repl_word

textalyzer/__init__.py

@@ -0,0 +1,9 @@
+# Developer : LORD KAY
+#
+#Permission is hereby granted, free of charge, to any person obtaining a copy
+#of this software and associated documentation files (the "Software"), to deal
+#in the Software without restriction, including without limitation the rights
+#to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+#copies of the Software.
+
+from __future__ import absolute_import, division, print_function

textalyzer-0.2.0.dist-info/METADATA

@@ -0,0 +1,79 @@
+Metadata-Version: 2.4
+Name: textalyzer
+Version: 0.2.0
+Summary: A text analyzer for repeating and contraction characters
+Home-page: https://github.com/LORD-KAY/Textalyzer
+Download-URL: https://github.com/LORD-KAY/Textalyzer/archive/refs/tags/v0.2.0.tar.gz
+Author: Lord Kay
+Author-email: offeilord@gmail.com
+License: MIT
+Project-URL: Source, https://github.com/LORD-KAY/Textalyzer
+Keywords: python,replacers,words,repeat,characters
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: nltk>=3
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: download-url
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Textalyzer
+Textalyzer is a lightweight python module or library to help ease analyzing of text or words in a particular sentence and manipulating it.
+Textalyzer analyzes repeating words and contracted words or contractions.
+
+# Class Functions Involved in this module
+  [-] ContractionReplacers <br>
+  [-] RepeatingReplacers
+
+# Usage
+  -Place the file in a folder where you have either read or write and read permisson. Eg. /opinionmining/lib/Textalyzer.py<br/>
+  -Import the module into your application.<br/>
+   <hr/> 
+    from opinionmining.lib.Textalyzer import "Function To Use" <br>
+    sample = "I can't wait for the football match" <br>
+    object = ContractionReplacers() <br>
+    data = object.text_replacers(sample)<br>
+
+# Sample
+  ## Repeating words
+  - Repeating words like helloooooooooooo - textalyzer help format this word by removing the o's to its normal word "hello"<br/>
+  - Contractions like I'm - Textalyzer help format this word by converting it to it's normal word "I am"
+# Dependencies
+- nltk
+- Download the WordNet corpus before using `RepeatingReplacers`: `python -m nltk.downloader wordnet`
+# PyPI
+- Textalyzer is available at python package index.
+  ## Installation Guide
+    - Download textalyzer using pip<br>
+    - pip install textalyzer<br>
+    - Import textalyzer into your project by using ```from textalyzer import Textalyzer``` depending on the function you want to use.<br>
+    - Then use ```replacer = Textalyzer.ContractionReplacers()``` and ```repeat = Textalyzer.RepeatingReplacers()``` <br>
+    -    ## Or
+    - Simple do ```import textalyzer``` <br>
+    - Then Use ``` data = textalyzer.Textalyzer ``` <br>
+    -   ``` replacer  = data.ContractionReplacers() ``` <br>
+    
+  ## Alternatively
+    - [x] You can download the tarball file from `pypi.python.org/pypi/textalyzer`
+    - [x] Extract the tarball file
+    - [x] Navigate into the extracted folder and install using `python setup.py install`
+    
+  **To Check Whether it's installed**
+  - type  `pip freeze` to display the list of installed packages
+# Why This
+- Textalyzer is mostly used by python programmers who are more involved with Natural Language Processing , Machine Learning, Text Extraction and others.

textalyzer-0.2.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+textalyzer/Textalyzer.py,sha256=PFN0MGn2qOK_mlp1ItCYSBMtnGttNqZrFOXTLLzeGFg,2121
+textalyzer/__init__.py,sha256=5WLSQ9h-m7dFdC28l8nXvMTsfjCojL7Uggjjr5H-4Yw,425
+textalyzer-0.2.0.dist-info/licenses/LICENSE.txt,sha256=OTAFEvyRVzwgK6ViyjvpQVaZFDzhI2pFCGcE3L9qrX0,1065
+textalyzer-0.2.0.dist-info/METADATA,sha256=sRx0aD-V965nho9KBUNM3ghBjyhMg8Ry9QrXae9hp4M,3245
+textalyzer-0.2.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+textalyzer-0.2.0.dist-info/top_level.txt,sha256=Vg5tngIh2SweYsldYYulvgcyDrncTxZ8ZHSipP2DAkw,11
+textalyzer-0.2.0.dist-info/RECORD,,

textalyzer-0.2.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

textalyzer-0.2.0.dist-info/licenses/LICENSE.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2018 Lord Kay
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

textalyzer-0.2.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+textalyzer