textclass-en 0.1.0__tar.gz

textclass_en-0.1.0/PKG-INFO

@@ -0,0 +1,18 @@
+Metadata-Version: 2.4
+Name: textclass-en
+Version: 0.1.0
+Summary: Extract keywords from English text
+Description-Content-Type: text/markdown
+
+# textclass-en
+A simple, fast Python library to extract keywords from English text.
+
+## Quick Start
+```python
+import textclass_en
+
+textclass_en.textclass("The quick brown fox jumped over the lazy dog") # result: ['quick', 'fox', 'jumped']
+textclass_en.textclass("The quick brown fox jumped over the lazy dog", max_keywords=10) # result: ['quick', 'fox', 'jumped', 'lazy', 'dog']
+textclass_en.textclass("The company 'OpenBrain' is about to go bankrupt because of their newest AI model.") # result: ['company', 'openbrain', 'bankrupt']
+textclass_en.textclass("The company 'OpenBrain' is about to go bankrupt because of their newest AI model.", max_keywords=10) # result: ['company', 'openbrain', 'bankrupt', 'newest', 'ai', 'model']
+```

textclass_en-0.1.0/README.md

@@ -0,0 +1,12 @@
+# textclass-en
+A simple, fast Python library to extract keywords from English text.
+
+## Quick Start
+```python
+import textclass_en
+
+textclass_en.textclass("The quick brown fox jumped over the lazy dog") # result: ['quick', 'fox', 'jumped']
+textclass_en.textclass("The quick brown fox jumped over the lazy dog", max_keywords=10) # result: ['quick', 'fox', 'jumped', 'lazy', 'dog']
+textclass_en.textclass("The company 'OpenBrain' is about to go bankrupt because of their newest AI model.") # result: ['company', 'openbrain', 'bankrupt']
+textclass_en.textclass("The company 'OpenBrain' is about to go bankrupt because of their newest AI model.", max_keywords=10) # result: ['company', 'openbrain', 'bankrupt', 'newest', 'ai', 'model']
+```

textclass_en-0.1.0/pyproject.toml

@@ -0,0 +1,10 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "textclass-en"
+version = "0.1.0"
+description = "Extract keywords from English text"
+readme = "README.md"
+dependencies = []

textclass_en-0.1.0/src/textclass_en/__init__.py

@@ -0,0 +1 @@
+from .main import textclass

textclass_en-0.1.0/src/textclass_en/main.py

@@ -0,0 +1,67 @@
+stopwords = (
+    "a", "about", "above", "across", "after", "afterwards", "again", "against", "all", "almost", 
+    "alone", "along", "already", "also", "although", "always", "am", "among", "amongst", "amoungst", 
+    "amount", "an", "and", "another", "any", "anyhow", "anyone", "anything", "anyway", "anywhere", 
+    "are", "around", "as", "at", "back", "be", "became", "because", "become", "becomes", "becoming", 
+    "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", 
+    "beyond", "bill", "both", "bottom", "but", "by", "call", "can", "cannot", "cant", "co", 
+    "computer", "con", "could", "couldnt", "cry", "de", "describe", "detail", "do", "done", "down", 
+    "due", "during", "each", "eg", "eight", "either", "eleven", "else", "elsewhere", "empty", 
+    "enough", "etc", "even", "ever", "every", "everyone", "everything", "everywhere", "except", 
+    "few", "fifteen", "fify", "fill", "find", "fire", "first", "five", "for", "former", "formerly", 
+    "forty", "found", "four", "from", "front", "full", "further", "get", "give", "go", "had", "has", 
+    "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby", "herein", "hereupon", 
+    "hers", "herself", "him", "himself", "his", "how", "however", "hundred", "i", "ie", "if", "in", 
+    "inc", "indeed", "interest", "into", "is", "it", "its", "itself", "keep", "last", "latter", 
+    "latterly", "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might", "mill", 
+    "mine", "more", "moreover", "most", "mostly", "move", "much", "must", "my", "myself", "name", 
+    "namely", "neither", "never", "nevertheless", "next", "nine", "no", "nobody", "none", "noone", 
+    "nor", "not", "nothing", "now", "nowhere", "of", "off", "often", "on", "once", "one", "only", 
+    "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over", "own", 
+    "part", "per", "perhaps", "please", "put", "rather", "re", "same", "see", "seem", "seemed", 
+    "seeming", "seems", "serious", "several", "she", "should", "show", "side", "since", "sincere", 
+    "six", "sixty", "so", "some", "somehow", "someone", "something", "sometime", "sometimes", 
+    "somewhere", "still", "such", "system", "take", "ten", "than", "that", "the", "their", "them", 
+    "themselves", "then", "thence", "there", "thereafter", "thereby", "therefore", "therein", 
+    "thereupon", "these", "they", "thick", "thin", "third", "this", "those", "though", "three", 
+    "through", "throughout", "thru", "thus", "to", "together", "too", "top", "toward", "towards", 
+    "twelve", "twenty", "two", "un", "under", "until", "up", "upon", "us", "very", "via", "was", 
+    "we", "well", "were", "what", "whatever", "when", "whence", "whenever", "where", "whereafter", 
+    "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", 
+    "whither", "who", "whoever", "whole", "whom", "whose", "why", "will", "with", "within", 
+    "without", "would", "yet", "you", "your", "yours", "yourself", "yourselves", "red", "green",
+    "blue", "magenta", "cyan", "teal", "brown", "orange", "white", "black", "pink"
+)
+
+def get_distance(s1, s2):
+    if len(s1) < len(s2):
+        return get_distance(s2, s1)
+    if not s2:
+        return len(s1)
+    previous_row = range(len(s2) + 1)
+    for i, c1 in enumerate(s1):
+        current_row = [i + 1]
+        for j, c2 in enumerate(s2):
+            insertions = previous_row[j + 1] + 1
+            deletions = current_row[j] + 1
+            substitutions = previous_row[j] + (c1 != c2)
+            current_row.append(min(insertions, deletions, substitutions))
+        previous_row = current_row
+    return previous_row[-1]
+
+def textclass(st, max_keywords=3):
+    tokens = "".join(char for char in st.lower() if char.isalpha() or char.isspace()).split(" ")
+    tokens = [tok for tok in tokens if tok not in stopwords]
+
+    for i, tok in enumerate(tokens):
+        match = next((existing for existing in tokens[:i] if get_distance(tok, existing) <= 1), None)
+        tokens[i] = match if match else tok
+
+    freq = {}
+    for tok in tokens:
+        if tok in freq:
+            freq[tok] += 1
+        else:
+            freq[tok] = 1
+
+    return sorted(freq, key=freq.get, reverse=True)[:max_keywords]