mail2task 0.4.0__tar.gz → 0.6.0__tar.gz

{mail2task-0.4.0 → mail2task-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mail2task
-Version: 0.4.0
+Version: 0.6.0
 Summary: Extract actionable tasks from emails using Python
 Author: Eby J Kavungal
 Project-URL: Homepage, https://github.com/EbyJK/mail2task
@@ -12,6 +12,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 Requires-Dist: dateparser
+Requires-Dist: spacy
 
 # mail2task
 
@@ -126,6 +127,21 @@ mail2task sample_email.txt --format markdown
 - Task management systems
 
 ---
+## NLP Features
+
+- Sentence splitting
+- Greeting/signature filtering
+- Due date extraction
+- Priority detection
+- Confidence scoring
+
+## NLP Engine
+
+mail2task uses spaCy for:
+- sentence segmentation
+- tokenization
+- action verb detection
+- lightweight NLP parsing
 
 ## Project Structure
 

{mail2task-0.4.0 → mail2task-0.6.0}/README.md

@@ -111,6 +111,21 @@ mail2task sample_email.txt --format markdown
 - Task management systems
 
 ---
+## NLP Features
+
+- Sentence splitting
+- Greeting/signature filtering
+- Due date extraction
+- Priority detection
+- Confidence scoring
+
+## NLP Engine
+
+mail2task uses spaCy for:
+- sentence segmentation
+- tokenization
+- action verb detection
+- lightweight NLP parsing
 
 ## Project Structure
 

{mail2task-0.4.0 → mail2task-0.6.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mail2task"
-version = "0.4.0"
+version = "0.6.0"
 description = "Extract actionable tasks from emails using Python"
 authors = [
   { name="Eby J Kavungal" }
@@ -13,7 +13,8 @@ readme = "README.md"
 requires-python = ">=3.9"
 
 dependencies = [
-  "dateparser"
+  "dateparser",
+  "spacy"
 ]
 
 keywords = ["nlp", "tasks", "email", "automation", "productivity"]

{mail2task-0.4.0 → mail2task-0.6.0}/src/mail2task/extractor.py

@@ -1,5 +1,9 @@
 import re
 import dateparser
+import spacy
+
+
+nlp = spacy.load("en_core_web_sm")
 
 
 ACTION_WORDS = [
@@ -15,7 +19,10 @@ ACTION_WORDS = [
     "email",
     "organize",
     "create",
-    "fix"
+    "fix",
+    "approve",
+    "confirm",
+    "deliver"
 ]
 
 
@@ -26,8 +33,30 @@ PRIORITY_KEYWORDS = {
 }
 
 
+IGNORE_PATTERNS = [
+    r"^hi\b",
+    r"^hello\b",
+    r"^thanks\b",
+    r"^thank you\b",
+    r"^regards\b",
+    r"^best\b",
+    r"^sincerely\b"
+]
+
+
 def clean_text(text: str):
-    return re.sub(r"\s+", " ", text).strip()
+    text = re.sub(r"\s+", " ", text)
+    return text.strip()
+
+
+def should_ignore(text: str):
+    text_lower = text.lower()
+
+    for pattern in IGNORE_PATTERNS:
+        if re.search(pattern, text_lower):
+            return True
+
+    return False
 
 
 def detect_priority(text: str):
@@ -53,30 +82,28 @@ def extract_due_date(text: str):
     return None
 
 
-def is_task_sentence(text: str):
-    text_lower = text.lower()
+def contains_action_verb(text: str):
+    doc = nlp(text)
+
+    for token in doc:
+        if token.lemma_.lower() in ACTION_WORDS:
+            return True
 
-    return any(word in text_lower for word in ACTION_WORDS)
+    return False
 
 
 def calculate_confidence(text: str, due_date, priority):
     score = 0.4
 
-    text_lower = text.lower()
-
-    # Action word boost
-    if any(word in text_lower for word in ACTION_WORDS):
+    if contains_action_verb(text):
         score += 0.25
 
-    # Due date boost
     if due_date:
         score += 0.2
 
-    # Priority boost
     if priority != "normal":
         score += 0.1
 
-    # Sentence length quality
     word_count = len(text.split())
 
     if 4 <= word_count <= 20:
@@ -86,27 +113,28 @@ def calculate_confidence(text: str, due_date, priority):
 
 
 def extract_tasks(email_text: str):
-    lines = email_text.splitlines()
+    doc = nlp(email_text)
 
     tasks = []
     seen_titles = set()
 
-    for line in lines:
-        line = clean_text(line)
+    for sent in doc.sents:
+
+        sentence = clean_text(sent.text)
 
-        if not line:
+        if should_ignore(sentence):
             continue
 
-        if len(line.split()) < 3:
+        if len(sentence.split()) < 3:
             continue
 
-        if not is_task_sentence(line):
+        if not contains_action_verb(sentence):
             continue
 
         title = re.sub(
             r"\b(please|kindly)\b",
             "",
-            line,
+            sentence,
             flags=re.IGNORECASE
         ).strip()
 
@@ -115,11 +143,11 @@ def extract_tasks(email_text: str):
 
         seen_titles.add(title.lower())
 
-        due_date = extract_due_date(line)
-        priority = detect_priority(line)
+        due_date = extract_due_date(sentence)
+        priority = detect_priority(sentence)
 
         confidence = calculate_confidence(
-            line,
+            sentence,
             due_date,
             priority
         )

{mail2task-0.4.0 → mail2task-0.6.0}/src/mail2task.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mail2task
-Version: 0.4.0
+Version: 0.6.0
 Summary: Extract actionable tasks from emails using Python
 Author: Eby J Kavungal
 Project-URL: Homepage, https://github.com/EbyJK/mail2task
@@ -12,6 +12,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 Requires-Dist: dateparser
+Requires-Dist: spacy
 
 # mail2task
 
@@ -126,6 +127,21 @@ mail2task sample_email.txt --format markdown
 - Task management systems
 
 ---
+## NLP Features
+
+- Sentence splitting
+- Greeting/signature filtering
+- Due date extraction
+- Priority detection
+- Confidence scoring
+
+## NLP Engine
+
+mail2task uses spaCy for:
+- sentence segmentation
+- tokenization
+- action verb detection
+- lightweight NLP parsing
 
 ## Project Structure
 

{mail2task-0.4.0 → mail2task-0.6.0}/src/mail2task.egg-info/requires.txt

@@ -1 +1,2 @@
 dateparser
+spacy