mail2task 0.5.0__tar.gz → 0.7.0__tar.gz

{mail2task-0.5.0 → mail2task-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mail2task
-Version: 0.5.0
+Version: 0.7.0
 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
 
@@ -134,6 +135,23 @@ mail2task sample_email.txt --format markdown
 - Priority detection
 - Confidence scoring
 
+## NLP Engine
+
+mail2task uses spaCy for:
+- sentence segmentation
+- tokenization
+- action verb detection
+- lightweight NLP parsing
+
+## `.eml` Email Support
+
+mail2task can process raw email files directly.
+
+```bash
+mail2task sample_email.eml --pretty
+```
+
+
 ## Project Structure
 
 ```text

{mail2task-0.5.0 → mail2task-0.7.0}/README.md

@@ -119,6 +119,23 @@ mail2task sample_email.txt --format markdown
 - Priority detection
 - Confidence scoring
 
+## NLP Engine
+
+mail2task uses spaCy for:
+- sentence segmentation
+- tokenization
+- action verb detection
+- lightweight NLP parsing
+
+## `.eml` Email Support
+
+mail2task can process raw email files directly.
+
+```bash
+mail2task sample_email.eml --pretty
+```
+
+
 ## Project Structure
 
 ```text

{mail2task-0.5.0 → mail2task-0.7.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mail2task"
-version = "0.5.0"
+version = "0.7.0"
 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-0.5.0 → mail2task-0.7.0}/src/mail2task/cli.py

@@ -2,6 +2,7 @@ import argparse
 import json
 import csv
 from .extractor import extract_tasks
+from .email_parser import extract_email_body
 
 
 def save_csv(tasks, output_file):
@@ -57,8 +58,11 @@ def main():
     args = parser.parse_args()
 
     try:
-        with open(args.file, "r", encoding="utf-8") as f:
-            content = f.read()
+        if args.file.endswith(".eml"):
+            content=extract_email_body(args.file)
+        else:
+            with open(args.file, "r", encoding="utf-8") as f:
+                content = f.read()
 
         tasks = extract_tasks(content)
 

mail2task-0.7.0/src/mail2task/email_parser.py

@@ -0,0 +1,22 @@
+from email import policy
+from email.parser import BytesParser
+
+
+def extract_email_body(file_path: str):
+    with open(file_path, "rb") as f:
+        msg = BytesParser(policy=policy.default).parse(f)
+
+    # Prefer plain text body
+    if msg.is_multipart():
+
+        for part in msg.walk():
+
+            content_type = part.get_content_type()
+
+            if content_type == "text/plain":
+                return part.get_content()
+
+    else:
+        return msg.get_content()
+
+    return ""

{mail2task-0.5.0 → mail2task-0.7.0}/src/mail2task/extractor.py

@@ -1,5 +1,9 @@
 import re
 import dateparser
+import spacy
+
+
+nlp = spacy.load("en_core_web_sm")
 
 
 ACTION_WORDS = [
@@ -78,18 +82,20 @@ 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)
 
-    return any(word in text_lower for word in ACTION_WORDS)
+    for token in doc:
+        if token.lemma_.lower() in ACTION_WORDS:
+            return True
+
+    return False
 
 
 def calculate_confidence(text: str, due_date, priority):
     score = 0.4
 
-    text_lower = text.lower()
-
-    if any(word in text_lower for word in ACTION_WORDS):
+    if contains_action_verb(text):
         score += 0.25
 
     if due_date:
@@ -106,23 +112,15 @@ def calculate_confidence(text: str, due_date, priority):
     return round(min(score, 0.99), 2)
 
 
-def split_sentences(email_text: str):
-    sentences = re.split(r"[.\n]+", email_text)
-
-    return [
-        clean_text(sentence)
-        for sentence in sentences
-        if clean_text(sentence)
-    ]
-
-
 def extract_tasks(email_text: str):
-    sentences = split_sentences(email_text)
+    doc = nlp(email_text)
 
     tasks = []
     seen_titles = set()
 
-    for sentence in sentences:
+    for sent in doc.sents:
+
+        sentence = clean_text(sent.text)
 
         if should_ignore(sentence):
             continue
@@ -130,7 +128,7 @@ def extract_tasks(email_text: str):
         if len(sentence.split()) < 3:
             continue
 
-        if not is_task_sentence(sentence):
+        if not contains_action_verb(sentence):
             continue
 
         title = re.sub(

{mail2task-0.5.0 → mail2task-0.7.0}/src/mail2task.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mail2task
-Version: 0.5.0
+Version: 0.7.0
 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
 
@@ -134,6 +135,23 @@ mail2task sample_email.txt --format markdown
 - Priority detection
 - Confidence scoring
 
+## NLP Engine
+
+mail2task uses spaCy for:
+- sentence segmentation
+- tokenization
+- action verb detection
+- lightweight NLP parsing
+
+## `.eml` Email Support
+
+mail2task can process raw email files directly.
+
+```bash
+mail2task sample_email.eml --pretty
+```
+
+
 ## Project Structure
 
 ```text

{mail2task-0.5.0 → mail2task-0.7.0}/src/mail2task.egg-info/SOURCES.txt

@@ -2,6 +2,7 @@ README.md
 pyproject.toml
 src/mail2task/__init__.py
 src/mail2task/cli.py
+src/mail2task/email_parser.py
 src/mail2task/extractor.py
 src/mail2task/parser.py
 src/mail2task.egg-info/PKG-INFO

{mail2task-0.5.0 → mail2task-0.7.0}/src/mail2task.egg-info/requires.txt

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