mail2task 0.3.0__tar.gz → 0.5.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {mail2task-0.3.0 → mail2task-0.5.0}/PKG-INFO +27 -1
- {mail2task-0.3.0 → mail2task-0.5.0}/README.md +26 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/pyproject.toml +1 -1
- mail2task-0.5.0/src/mail2task/cli.py +99 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task/extractor.py +46 -16
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task.egg-info/PKG-INFO +27 -1
- mail2task-0.3.0/src/mail2task/cli.py +0 -52
- {mail2task-0.3.0 → mail2task-0.5.0}/setup.cfg +0 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task/__init__.py +0 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task/parser.py +0 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task.egg-info/SOURCES.txt +0 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task.egg-info/dependency_links.txt +0 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task.egg-info/entry_points.txt +0 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task.egg-info/requires.txt +0 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/src/mail2task.egg-info/top_level.txt +0 -0
- {mail2task-0.3.0 → mail2task-0.5.0}/tests/test_extractor.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: mail2task
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.5.0
|
|
4
4
|
Summary: Extract actionable tasks from emails using Python
|
|
5
5
|
Author: Eby J Kavungal
|
|
6
6
|
Project-URL: Homepage, https://github.com/EbyJK/mail2task
|
|
@@ -96,6 +96,25 @@ mail2task sample_email.txt --pretty
|
|
|
96
96
|
mail2task sample_email.txt --output tasks.json
|
|
97
97
|
```
|
|
98
98
|
|
|
99
|
+
|
|
100
|
+
## Export Formats
|
|
101
|
+
|
|
102
|
+
### JSON
|
|
103
|
+
```bash
|
|
104
|
+
mail2task sample_email.txt --format json
|
|
105
|
+
```
|
|
106
|
+
|
|
107
|
+
### CSV
|
|
108
|
+
```bash
|
|
109
|
+
mail2task sample_email.txt --format csv
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
### Markdown
|
|
113
|
+
```bash
|
|
114
|
+
mail2task sample_email.txt --format markdown
|
|
115
|
+
```
|
|
116
|
+
|
|
117
|
+
|
|
99
118
|
---
|
|
100
119
|
|
|
101
120
|
## Example Use Cases
|
|
@@ -107,6 +126,13 @@ mail2task sample_email.txt --output tasks.json
|
|
|
107
126
|
- Task management systems
|
|
108
127
|
|
|
109
128
|
---
|
|
129
|
+
## NLP Features
|
|
130
|
+
|
|
131
|
+
- Sentence splitting
|
|
132
|
+
- Greeting/signature filtering
|
|
133
|
+
- Due date extraction
|
|
134
|
+
- Priority detection
|
|
135
|
+
- Confidence scoring
|
|
110
136
|
|
|
111
137
|
## Project Structure
|
|
112
138
|
|
|
@@ -81,6 +81,25 @@ mail2task sample_email.txt --pretty
|
|
|
81
81
|
mail2task sample_email.txt --output tasks.json
|
|
82
82
|
```
|
|
83
83
|
|
|
84
|
+
|
|
85
|
+
## Export Formats
|
|
86
|
+
|
|
87
|
+
### JSON
|
|
88
|
+
```bash
|
|
89
|
+
mail2task sample_email.txt --format json
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
### CSV
|
|
93
|
+
```bash
|
|
94
|
+
mail2task sample_email.txt --format csv
|
|
95
|
+
```
|
|
96
|
+
|
|
97
|
+
### Markdown
|
|
98
|
+
```bash
|
|
99
|
+
mail2task sample_email.txt --format markdown
|
|
100
|
+
```
|
|
101
|
+
|
|
102
|
+
|
|
84
103
|
---
|
|
85
104
|
|
|
86
105
|
## Example Use Cases
|
|
@@ -92,6 +111,13 @@ mail2task sample_email.txt --output tasks.json
|
|
|
92
111
|
- Task management systems
|
|
93
112
|
|
|
94
113
|
---
|
|
114
|
+
## NLP Features
|
|
115
|
+
|
|
116
|
+
- Sentence splitting
|
|
117
|
+
- Greeting/signature filtering
|
|
118
|
+
- Due date extraction
|
|
119
|
+
- Priority detection
|
|
120
|
+
- Confidence scoring
|
|
95
121
|
|
|
96
122
|
## Project Structure
|
|
97
123
|
|
|
@@ -0,0 +1,99 @@
|
|
|
1
|
+
import argparse
|
|
2
|
+
import json
|
|
3
|
+
import csv
|
|
4
|
+
from .extractor import extract_tasks
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
def save_csv(tasks, output_file):
|
|
8
|
+
with open(output_file, "w", newline="", encoding="utf-8") as f:
|
|
9
|
+
writer = csv.DictWriter(
|
|
10
|
+
f,
|
|
11
|
+
fieldnames=["title", "due_date", "priority", "confidence"]
|
|
12
|
+
)
|
|
13
|
+
|
|
14
|
+
writer.writeheader()
|
|
15
|
+
writer.writerows(tasks)
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
def save_markdown(tasks, output_file):
|
|
19
|
+
with open(output_file, "w", encoding="utf-8") as f:
|
|
20
|
+
f.write("# Extracted Tasks\n\n")
|
|
21
|
+
|
|
22
|
+
for task in tasks:
|
|
23
|
+
f.write(f"## {task['title']}\n")
|
|
24
|
+
f.write(f"- Due Date: {task['due_date']}\n")
|
|
25
|
+
f.write(f"- Priority: {task['priority']}\n")
|
|
26
|
+
f.write(f"- Confidence: {task['confidence']}\n\n")
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
def main():
|
|
30
|
+
parser = argparse.ArgumentParser(
|
|
31
|
+
description="Extract actionable tasks from emails"
|
|
32
|
+
)
|
|
33
|
+
|
|
34
|
+
parser.add_argument(
|
|
35
|
+
"file",
|
|
36
|
+
help="Path to the email text file"
|
|
37
|
+
)
|
|
38
|
+
|
|
39
|
+
parser.add_argument(
|
|
40
|
+
"--pretty",
|
|
41
|
+
action="store_true",
|
|
42
|
+
help="Pretty print JSON output"
|
|
43
|
+
)
|
|
44
|
+
|
|
45
|
+
parser.add_argument(
|
|
46
|
+
"--format",
|
|
47
|
+
choices=["json", "csv", "markdown"],
|
|
48
|
+
default="json",
|
|
49
|
+
help="Output format"
|
|
50
|
+
)
|
|
51
|
+
|
|
52
|
+
parser.add_argument(
|
|
53
|
+
"--output",
|
|
54
|
+
help="Output file path"
|
|
55
|
+
)
|
|
56
|
+
|
|
57
|
+
args = parser.parse_args()
|
|
58
|
+
|
|
59
|
+
try:
|
|
60
|
+
with open(args.file, "r", encoding="utf-8") as f:
|
|
61
|
+
content = f.read()
|
|
62
|
+
|
|
63
|
+
tasks = extract_tasks(content)
|
|
64
|
+
|
|
65
|
+
# JSON handling
|
|
66
|
+
if args.format == "json":
|
|
67
|
+
result = (
|
|
68
|
+
json.dumps(tasks, indent=2)
|
|
69
|
+
if args.pretty
|
|
70
|
+
else json.dumps(tasks)
|
|
71
|
+
)
|
|
72
|
+
|
|
73
|
+
print(result)
|
|
74
|
+
|
|
75
|
+
if args.output:
|
|
76
|
+
with open(args.output, "w", encoding="utf-8") as out:
|
|
77
|
+
out.write(result)
|
|
78
|
+
|
|
79
|
+
# CSV handling
|
|
80
|
+
elif args.format == "csv":
|
|
81
|
+
output_file = args.output or "tasks.csv"
|
|
82
|
+
|
|
83
|
+
save_csv(tasks, output_file)
|
|
84
|
+
|
|
85
|
+
print(f"CSV saved to {output_file}")
|
|
86
|
+
|
|
87
|
+
# Markdown handling
|
|
88
|
+
elif args.format == "markdown":
|
|
89
|
+
output_file = args.output or "tasks.md"
|
|
90
|
+
|
|
91
|
+
save_markdown(tasks, output_file)
|
|
92
|
+
|
|
93
|
+
print(f"Markdown saved to {output_file}")
|
|
94
|
+
|
|
95
|
+
except FileNotFoundError:
|
|
96
|
+
print(f"File not found: {args.file}")
|
|
97
|
+
|
|
98
|
+
except Exception as e:
|
|
99
|
+
print(f"Error: {e}")
|
|
@@ -15,7 +15,10 @@ ACTION_WORDS = [
|
|
|
15
15
|
"email",
|
|
16
16
|
"organize",
|
|
17
17
|
"create",
|
|
18
|
-
"fix"
|
|
18
|
+
"fix",
|
|
19
|
+
"approve",
|
|
20
|
+
"confirm",
|
|
21
|
+
"deliver"
|
|
19
22
|
]
|
|
20
23
|
|
|
21
24
|
|
|
@@ -26,8 +29,30 @@ PRIORITY_KEYWORDS = {
|
|
|
26
29
|
}
|
|
27
30
|
|
|
28
31
|
|
|
32
|
+
IGNORE_PATTERNS = [
|
|
33
|
+
r"^hi\b",
|
|
34
|
+
r"^hello\b",
|
|
35
|
+
r"^thanks\b",
|
|
36
|
+
r"^thank you\b",
|
|
37
|
+
r"^regards\b",
|
|
38
|
+
r"^best\b",
|
|
39
|
+
r"^sincerely\b"
|
|
40
|
+
]
|
|
41
|
+
|
|
42
|
+
|
|
29
43
|
def clean_text(text: str):
|
|
30
|
-
|
|
44
|
+
text = re.sub(r"\s+", " ", text)
|
|
45
|
+
return text.strip()
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
def should_ignore(text: str):
|
|
49
|
+
text_lower = text.lower()
|
|
50
|
+
|
|
51
|
+
for pattern in IGNORE_PATTERNS:
|
|
52
|
+
if re.search(pattern, text_lower):
|
|
53
|
+
return True
|
|
54
|
+
|
|
55
|
+
return False
|
|
31
56
|
|
|
32
57
|
|
|
33
58
|
def detect_priority(text: str):
|
|
@@ -64,19 +89,15 @@ def calculate_confidence(text: str, due_date, priority):
|
|
|
64
89
|
|
|
65
90
|
text_lower = text.lower()
|
|
66
91
|
|
|
67
|
-
# Action word boost
|
|
68
92
|
if any(word in text_lower for word in ACTION_WORDS):
|
|
69
93
|
score += 0.25
|
|
70
94
|
|
|
71
|
-
# Due date boost
|
|
72
95
|
if due_date:
|
|
73
96
|
score += 0.2
|
|
74
97
|
|
|
75
|
-
# Priority boost
|
|
76
98
|
if priority != "normal":
|
|
77
99
|
score += 0.1
|
|
78
100
|
|
|
79
|
-
# Sentence length quality
|
|
80
101
|
word_count = len(text.split())
|
|
81
102
|
|
|
82
103
|
if 4 <= word_count <= 20:
|
|
@@ -85,28 +106,37 @@ def calculate_confidence(text: str, due_date, priority):
|
|
|
85
106
|
return round(min(score, 0.99), 2)
|
|
86
107
|
|
|
87
108
|
|
|
109
|
+
def split_sentences(email_text: str):
|
|
110
|
+
sentences = re.split(r"[.\n]+", email_text)
|
|
111
|
+
|
|
112
|
+
return [
|
|
113
|
+
clean_text(sentence)
|
|
114
|
+
for sentence in sentences
|
|
115
|
+
if clean_text(sentence)
|
|
116
|
+
]
|
|
117
|
+
|
|
118
|
+
|
|
88
119
|
def extract_tasks(email_text: str):
|
|
89
|
-
|
|
120
|
+
sentences = split_sentences(email_text)
|
|
90
121
|
|
|
91
122
|
tasks = []
|
|
92
123
|
seen_titles = set()
|
|
93
124
|
|
|
94
|
-
for
|
|
95
|
-
line = clean_text(line)
|
|
125
|
+
for sentence in sentences:
|
|
96
126
|
|
|
97
|
-
if
|
|
127
|
+
if should_ignore(sentence):
|
|
98
128
|
continue
|
|
99
129
|
|
|
100
|
-
if len(
|
|
130
|
+
if len(sentence.split()) < 3:
|
|
101
131
|
continue
|
|
102
132
|
|
|
103
|
-
if not is_task_sentence(
|
|
133
|
+
if not is_task_sentence(sentence):
|
|
104
134
|
continue
|
|
105
135
|
|
|
106
136
|
title = re.sub(
|
|
107
137
|
r"\b(please|kindly)\b",
|
|
108
138
|
"",
|
|
109
|
-
|
|
139
|
+
sentence,
|
|
110
140
|
flags=re.IGNORECASE
|
|
111
141
|
).strip()
|
|
112
142
|
|
|
@@ -115,11 +145,11 @@ def extract_tasks(email_text: str):
|
|
|
115
145
|
|
|
116
146
|
seen_titles.add(title.lower())
|
|
117
147
|
|
|
118
|
-
due_date = extract_due_date(
|
|
119
|
-
priority = detect_priority(
|
|
148
|
+
due_date = extract_due_date(sentence)
|
|
149
|
+
priority = detect_priority(sentence)
|
|
120
150
|
|
|
121
151
|
confidence = calculate_confidence(
|
|
122
|
-
|
|
152
|
+
sentence,
|
|
123
153
|
due_date,
|
|
124
154
|
priority
|
|
125
155
|
)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: mail2task
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.5.0
|
|
4
4
|
Summary: Extract actionable tasks from emails using Python
|
|
5
5
|
Author: Eby J Kavungal
|
|
6
6
|
Project-URL: Homepage, https://github.com/EbyJK/mail2task
|
|
@@ -96,6 +96,25 @@ mail2task sample_email.txt --pretty
|
|
|
96
96
|
mail2task sample_email.txt --output tasks.json
|
|
97
97
|
```
|
|
98
98
|
|
|
99
|
+
|
|
100
|
+
## Export Formats
|
|
101
|
+
|
|
102
|
+
### JSON
|
|
103
|
+
```bash
|
|
104
|
+
mail2task sample_email.txt --format json
|
|
105
|
+
```
|
|
106
|
+
|
|
107
|
+
### CSV
|
|
108
|
+
```bash
|
|
109
|
+
mail2task sample_email.txt --format csv
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
### Markdown
|
|
113
|
+
```bash
|
|
114
|
+
mail2task sample_email.txt --format markdown
|
|
115
|
+
```
|
|
116
|
+
|
|
117
|
+
|
|
99
118
|
---
|
|
100
119
|
|
|
101
120
|
## Example Use Cases
|
|
@@ -107,6 +126,13 @@ mail2task sample_email.txt --output tasks.json
|
|
|
107
126
|
- Task management systems
|
|
108
127
|
|
|
109
128
|
---
|
|
129
|
+
## NLP Features
|
|
130
|
+
|
|
131
|
+
- Sentence splitting
|
|
132
|
+
- Greeting/signature filtering
|
|
133
|
+
- Due date extraction
|
|
134
|
+
- Priority detection
|
|
135
|
+
- Confidence scoring
|
|
110
136
|
|
|
111
137
|
## Project Structure
|
|
112
138
|
|
|
@@ -1,52 +0,0 @@
|
|
|
1
|
-
import argparse
|
|
2
|
-
import json
|
|
3
|
-
from .extractor import extract_tasks
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
def main():
|
|
7
|
-
parser = argparse.ArgumentParser(
|
|
8
|
-
description="Extract actionable tasks from emails"
|
|
9
|
-
)
|
|
10
|
-
|
|
11
|
-
parser.add_argument(
|
|
12
|
-
"file",
|
|
13
|
-
help="Path to the email text file"
|
|
14
|
-
)
|
|
15
|
-
|
|
16
|
-
parser.add_argument(
|
|
17
|
-
"--pretty",
|
|
18
|
-
action="store_true",
|
|
19
|
-
help="Pretty print the output"
|
|
20
|
-
)
|
|
21
|
-
|
|
22
|
-
parser.add_argument(
|
|
23
|
-
"--output",
|
|
24
|
-
help="Save output to a JSON file"
|
|
25
|
-
)
|
|
26
|
-
|
|
27
|
-
args = parser.parse_args()
|
|
28
|
-
|
|
29
|
-
try:
|
|
30
|
-
with open(args.file, "r", encoding="utf-8") as f:
|
|
31
|
-
content = f.read()
|
|
32
|
-
|
|
33
|
-
tasks = extract_tasks(content)
|
|
34
|
-
|
|
35
|
-
if args.pretty:
|
|
36
|
-
result = json.dumps(tasks, indent=2)
|
|
37
|
-
else:
|
|
38
|
-
result = json.dumps(tasks)
|
|
39
|
-
|
|
40
|
-
print(result)
|
|
41
|
-
|
|
42
|
-
if args.output:
|
|
43
|
-
with open(args.output, "w", encoding="utf-8") as out_file:
|
|
44
|
-
out_file.write(result)
|
|
45
|
-
|
|
46
|
-
print(f"\nSaved output to {args.output}")
|
|
47
|
-
|
|
48
|
-
except FileNotFoundError:
|
|
49
|
-
print(f"File not found: {args.file}")
|
|
50
|
-
|
|
51
|
-
except Exception as e:
|
|
52
|
-
print(f"Error: {e}")
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|