Merge pull request #8 from nsoma97/add_readme

Add readme

.github/workflows/datetime-parser-cicd.yaml

@@ -24,10 +24,10 @@ jobs:
         pip install -r requirements.txt
     - name: Static analysis with mypy
       run: |
-        python -m mypy --ignore-missing-imports src
+        python -m mypy --ignore-missing-imports hun_date_parser
     - name: Static analysis with flake8
       run: |
-        python -m flake8 --max-line-length=120 --per-file-ignores='patterns.py:E501' src
+        python -m flake8 --max-line-length=120 --per-file-ignores='patterns.py:E501' hun_date_parser
     - name: Test with pytest
       run: |
         pytest

README.md

@@ -1 +1,66 @@
-# hun-date-parser
+<h1 align="center">Hungarian Date Parser</h1>
+
+<p align="center">
+    <i>A tool for extracting datetime intervals from Hungarian sentences and turning datetime objects into Hungarian text.</i>
+</p>
+
+
+<div align="center">
+    <img src="https://img.shields.io/github/stars/nsoma97/hun-date-parser" alt="Stars Badge"/>
+    <img src="https://img.shields.io/github/issues/nsoma97/hun-date-parser" alt="Issues Badge"/>
+    <img src="https://img.shields.io/github/license/nsoma97/hun-date-parser?color=2b9348" alt="License Badge"/>
+    <img src="https://img.shields.io/github/workflow/status/nsoma97/hun-date-parser/Datetime Parser Pipeline" alt="Tests"/>
+</div>
+
+<br>
+
+
+Install and try the package with `pip install hun-date-parser`.
+
+## :fire: Usage
+
+If not specified otherwise, relative dates (eg.: tomorrow, next week, etc.) are calculated relative to the current datetime, at the time when the DatetimeExtractor is instanciated.
+
+```python
+from hun_date_parser import DatetimeExtractor
+
+datetime_extractor = DatetimeExtractor()
+
+datetime_extractor.parse_datetime('találkozzunk jövő kedd délután!')
+# {'start_date': datetime.datetime(2020, 12, 29, 12, 0), 'end_date': datetime.datetime(2020, 12, 29, 17, 59, 59)}
+
+datetime_extractor.parse_datetime('találkozzunk szombaton háromnegyed nyolc előtt két perccel')
+# {'start_date': datetime.datetime(2020, 12, 26, 7, 43), 'end_date': datetime.datetime(2020, 12, 26, 7, 43, 59)}
+```
+The date parser is also capable of parsing explicit intervals from the text even when only one side of the interval is specified.
+```python
+datetime_extractor.parse_datetime('2020 decemberétől 2021 januárig')
+# {'start_date': datetime.datetime(2020, 12, 1, 0, 0), 'end_date': datetime.datetime(2021, 1, 31, 23, 59, 59)}
+
+
+datetime_extractor.parse_datetime('2020 decemberéig')
+# {'start_date': None, 'end_date': datetime.datetime(2020, 12, 31, 23, 59, 59)}
+```
+
+The library is also capable of turning datetime objects into their Hungarian text representation.
+
+```python
+from datetime import datetime
+from hun_date_parser import DatetimeTextualizer
+
+datetime_textualizer = DatetimeTextualizer()
+
+datetime_textualizer.generate_candidates()
+
+datetime_textualizer.generate_candidates(datetime(2020, 12, 20, 18, 34), time_precision=2)
+# {'date': ['ezen a héten vasárnap', '2020 december 20'],
+#  'times': ['tizennyolc óra harmincnégy perc', '18:34', 'este hat óra harmincnégy perc', 'este fél 7 után 4 perccel']}
+```
+
+## :pencil: License
+
+This project is licensed under [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) license. Feel free to use it in your own projects.
+
+## :wrench: Contribute
+
+Any help or feedback in further developing the library is welcome!

hun_date_parser/__init__.py

@@ -0,0 +1,4 @@
+from hun_date_parser.date_textualizer.datetime_textualizer import DatetimeTextualizer
+from hun_date_parser.date_parser.datetime_extractor import DatetimeExtractor
+
+__all__ = ["DatetimeTextualizer", "DatetimeExtractor"]

src/date_parser/date_parsers.py → hun_date_parser/date_parser/date_parsers.py

@@ -4,7 +4,7 @@
 
 from .patterns import (R_ISO_DATE, R_NAMED_MONTH, R_TODAY, R_TOMORROW, R_NTOMORROW, R_YESTERDAY, R_NYESTERDAY,
                        R_WEEKDAY, R_WEEK, R_YEAR)
-from src.utils import remove_accent, word_to_num, Year, Month, Week, Day
+from hun_date_parser.utils import remove_accent, word_to_num, Year, Month, Week, Day
 
 
 def match_iso_date(s: str) -> List[Dict[str, Any]]:

src/date_parser/datetime_extractor.py → hun_date_parser/date_parser/datetime_extractor.py

@@ -5,11 +5,12 @@
 from typing import Dict, List, Union
 from copy import copy
 
-from src.date_parser.structure_parsers import match_multi_match, match_interval
-from src.date_parser.date_parsers import (match_named_month, match_iso_date, match_weekday, match_relative_day,
-                                          match_week, match_named_year)
-from src.date_parser.time_parsers import match_digi_clock, match_time_words
-from src.utils import Year, Month, Week, Day, Daypart, Hour, Minute, monday_of_calenderweek
+from hun_date_parser.date_parser.structure_parsers import match_multi_match, match_interval
+from hun_date_parser.date_parser.date_parsers import (match_named_month, match_iso_date, match_weekday,
+                                                      match_relative_day,
+                                                      match_week, match_named_year)
+from hun_date_parser.date_parser.time_parsers import match_digi_clock, match_time_words
+from hun_date_parser.utils import Year, Month, Week, Day, Daypart, Hour, Minute, monday_of_calenderweek
 
 daypart_mapping = [
     (3, 5),
@@ -25,8 +26,6 @@ def assamble_datetime(now: datetime, dateparts: Union[List[Union[Year, Month, We
                       bottom: bool = True):
     res_dt = []
 
-    print(dateparts)
-
     if dateparts == 'OPEN':
         return None
     if not dateparts:
@@ -78,10 +77,12 @@ def assamble_datetime(now: datetime, dateparts: Union[List[Union[Year, Month, We
                 dp = dp_match[0][0]
                 if bottom:
                     res_dt.append(daypart_mapping[dp][0])
-                else:
-                    y, m, d, h, mi, se = res_dt
-                    next_day = datetime(y, m, d, h, mi, se) + timedelta(days=1)
+                elif dp == 5:
+                    y, m, d = res_dt
+                    next_day = datetime(y, m, d) + timedelta(days=1)
                     res_dt = [next_day.year, next_day.month, next_day.day, daypart_mapping[dp][1]]
+                else:
+                    res_dt.append(daypart_mapping[dp][1])
 
         if date_type == Hour and len(res_dt) == 3:
             if dp_match:

src/date_parser/time_parsers.py → hun_date_parser/date_parser/time_parsers.py

@@ -3,7 +3,7 @@
 from typing import Dict, List, Any
 
 from .patterns import R_DIGI, R_HOUR_MIN, R_HOUR_MIN_REV
-from src.utils import remove_accent, word_to_num, Hour, Minute, Daypart
+from hun_date_parser.utils import remove_accent, word_to_num, Hour, Minute, Daypart
 
 NAN = -1
 

src/date_textualizer/datetime_textualizer.py → hun_date_parser/date_textualizer/datetime_textualizer.py

@@ -1,7 +1,8 @@
 from datetime import datetime
 
-from src.date_textualizer.date2text import date2text, date2full_text
-from src.date_textualizer.time2text import time2absolutetexttime, time2digi, time2relitivetexttime, time2lifelike
+from hun_date_parser.date_textualizer.date2text import date2text, date2full_text
+from hun_date_parser.date_textualizer.time2text import time2absolutetexttime, time2digi, time2relitivetexttime, \
+    time2lifelike
 
 
 class DatetimeTextualizer:

src/date_textualizer/time2text.py → hun_date_parser/date_textualizer/time2text.py

@@ -1,6 +1,6 @@
 from datetime import time
 
-from src.utils import num_to_word
+from hun_date_parser.utils import num_to_word
 
 hours_word = {
     0: 'nulla',

setup.py

@@ -0,0 +1,22 @@
+import setuptools
+
+with open("README.md", "r", encoding="utf-8") as fh:
+    long_description = fh.read()
+
+setuptools.setup(
+    name="hun-date-parser",
+    version="0.0.1",
+    author="Soma Nagy",
+    author_email="nagysomabalint@gmail.com",
+    description="A tool for extracting datetime intervals from Hungarian sentences and turning datetime objects into Hungarian text.",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/nsoma97/hun-date-parser",
+    packages=setuptools.find_packages(),
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: Apache Software License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.6',
+)

test/test_date_parsers.py

@@ -1,8 +1,8 @@
 from datetime import datetime
 
-from src.date_parser.date_parsers import Year, Month, Week, Day
-from src.date_parser.date_parsers import (match_iso_date, match_named_month, match_relative_day, match_weekday,
-                                          match_week, match_named_year)
+from hun_date_parser.date_parser.date_parsers import Year, Month, Week, Day
+from hun_date_parser.date_parser.date_parsers import (match_iso_date, match_named_month, match_relative_day, match_weekday,
+                                                      match_week, match_named_year)
 
 
 def test_match_iso_date():

test/test_datetime2text.py

@@ -1,6 +1,6 @@
 from datetime import time
 
-from src.date_textualizer.time2text import time2lifelike
+from hun_date_parser.date_textualizer.time2text import time2lifelike
 
 
 def test_time2lifelike():

test/test_datetime_extractor.py

@@ -1,6 +1,6 @@
 from datetime import datetime
 
-from src.date_parser.datetime_extractor import DatetimeExtractor, assamble_datetime
+from hun_date_parser.date_parser.datetime_extractor import DatetimeExtractor, assamble_datetime
 
 
 def test_datetime_extractor():

test/test_structure_parsers.py

@@ -1,4 +1,4 @@
-from src.date_parser.structure_parsers import match_interval, match_multi_match
+from hun_date_parser.date_parser.structure_parsers import match_interval, match_multi_match
 
 
 def test_match_interval():

test/test_time_parsers.py

@@ -1,5 +1,5 @@
-from src.utils import Daypart, Hour, Minute
-from src.date_parser.time_parsers import match_digi_clock, match_time_words
+from hun_date_parser.utils import Daypart, Hour, Minute
+from hun_date_parser.date_parser.time_parsers import match_digi_clock, match_time_words
 
 
 def test_match_digi_clock():

test/test_utils.py

@@ -1,4 +1,4 @@
-from src.utils import word_to_num, num_to_word, remove_accent
+from hun_date_parser.utils import word_to_num, num_to_word, remove_accent
 
 
 def test_remove_accent():