dateparser 1.1.8__tar.gz → 1.2.1__tar.gz

{dateparser-1.1.8 → dateparser-1.2.1}/HISTORY.rst

@@ -3,10 +3,55 @@
 History
 =======
 
+1.2.1 (2025-02-05)
+------------------
+
+Fixes:
+
+- Fix PytzUsageWarning (#1109)
+- Fix date_parser with prefer_month_of_year wrong results (#1224)
+- Fix skipped day when UTC and tz are different days (#1183)
+
+Improvements:
+
+- Avoid repeated loop over timezones (#1238)
+- Proofread README.rst (#1234)
+- Check for derived types for configuration (#1223)
+- Parse some abbreviated strings as relative dates (#1219)
+- Migrate from hijri-converter to hijridate (#1211)
+- Fixed ClusterFuzz build error by adding dateparser.data as a binary (#1208)
+- Fix an issue detected by OSSFuzz (#1203)
+- Support two-digit years in non-Gregorian calendars (#1187)
+- Refactored CI to run extras separately and test minimum versions of dependencies, replaced flake8 with ruff, fixed tests (#1248)
+- Set minimum versions for dependencies (#1248)
+- Limited ``numpy`` to 1.x when installing ``dateparser[fasttext]`` (#1248)
+
+
+1.2.0 (2023-11-17)
+------------------
+
+New features:
+
+- New ``PREFER_MONTH_OF_YEAR`` setting (#1146)
+
+Fixes:
+
+- Absolute years in Russian are no longer being treated as a number of years in
+  the past (#1129)
+
+Cleanups and internal improvements:
+
+- Removed the use of ``datetime.utcnow``, deprecated on Python 3.12 (#1179)
+- Applied Black formatting to the code base (#1158)
+- Initial integration with OSSFuzz (#1198)
+- Extended test cases (#1191)
+
+
 1.1.8 (2023-03-22)
 ------------------
 
 Improvements:
+
 - Improved date parsing for Chinese (#1148)
 - Improved date parsing for Czech (#1151)
 - Reorder language by popularity (#1152)

{dateparser-1.1.8 → dateparser-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: dateparser
-Version: 1.1.8
+Version: 1.2.1
 Summary: Date parsing library designed to parse dates from HTML pages
 Home-page: https://github.com/scrapinghub/dateparser
 Author: Scrapinghub
@@ -13,18 +13,39 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: BSD License
 Classifier: Natural Language :: English
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: Implementation :: CPython
-Requires-Python: >=3.7
+Requires-Python: >=3.8
+License-File: LICENSE
+License-File: AUTHORS.rst
+Requires-Dist: python-dateutil>=2.7.0
+Requires-Dist: pytz>=2024.2
+Requires-Dist: regex!=2019.02.19,!=2021.8.27,>=2015.06.24
+Requires-Dist: tzlocal>=0.2
 Provides-Extra: calendars
+Requires-Dist: convertdate>=2.2.1; extra == "calendars"
+Requires-Dist: hijridate; extra == "calendars"
 Provides-Extra: fasttext
+Requires-Dist: fasttext>=0.9.1; extra == "fasttext"
+Requires-Dist: numpy<2,>=1.19.3; extra == "fasttext"
 Provides-Extra: langdetect
-License-File: LICENSE
-License-File: AUTHORS.rst
+Requires-Dist: langdetect>=1.0.0; extra == "langdetect"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: project-url
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 ==========================
 Introduction to dateparser
@@ -208,6 +229,16 @@ Incomplete Dates
     >>> parse('August', settings={'PREFER_DATES_FROM': 'past'})
     datetime.datetime(2015, 8, 15, 0, 0)
 
+    >>> import dateparser
+    >>> dateparser.parse("2015") # default behavior
+    datetime.datetime(2015, 3, 27, 0, 0)
+    >>> dateparser.parse("2015", settings={"PREFER_MONTH_OF_YEAR": "last"})
+    datetime.datetime(2015, 12, 27, 0, 0)
+    >>> dateparser.parse("2015", settings={"PREFER_MONTH_OF_YEAR": "first"})
+    datetime.datetime(2015, 1, 27, 0, 0)
+    >>> dateparser.parse("2015", settings={"PREFER_MONTH_OF_YEAR": "current"})
+    datetime.datetime(2015, 3, 27, 0, 0)
+
 You can also ignore parsing incomplete dates altogether by setting `STRICT_PARSING` flag as follows:
 
     >>> parse('December 2015', settings={'STRICT_PARSING': True})
@@ -241,13 +272,13 @@ Dependencies
 
   * dateutil_'s module ``relativedelta`` for its freshness parser.
   * convertdate_ to convert *Jalali* dates to *Gregorian*.
-  * hijri-converter_ to convert *Hijri* dates to *Gregorian*.
+  * hijridate_ to convert *Hijri* dates to *Gregorian*.
   * tzlocal_ to reliably get local timezone.
   * ruamel.yaml_ (optional) for operations on language files.
 
 .. _dateutil: https://pypi.python.org/pypi/python-dateutil
 .. _convertdate: https://pypi.python.org/pypi/convertdate
-.. _hijri-converter: https://pypi.python.org/pypi/hijri-converter
+.. _hijridate: https://pypi.python.org/pypi/hijridate
 .. _tzlocal: https://pypi.python.org/pypi/tzlocal
 .. _ruamel.yaml: https://pypi.python.org/pypi/ruamel.yaml
 
@@ -279,7 +310,7 @@ To be able to use them you need to install the `calendar` extra by typing:
     >>> HijriCalendar('17-01-1437 هـ 08:30 مساءً').get_date()
     DateData(date_obj=datetime.datetime(2015, 10, 30, 20, 30), period='day', locale=None)
 
-.. note:: `HijriCalendar` only works with Python ≥ 3.6.
+.. note:: `HijriCalendar` only works with Python ≥ 3.7.
 
 
 .. :changelog:
@@ -287,10 +318,55 @@ To be able to use them you need to install the `calendar` extra by typing:
 History
 =======
 
+1.2.1 (2025-02-05)
+------------------
+
+Fixes:
+
+- Fix PytzUsageWarning (#1109)
+- Fix date_parser with prefer_month_of_year wrong results (#1224)
+- Fix skipped day when UTC and tz are different days (#1183)
+
+Improvements:
+
+- Avoid repeated loop over timezones (#1238)
+- Proofread README.rst (#1234)
+- Check for derived types for configuration (#1223)
+- Parse some abbreviated strings as relative dates (#1219)
+- Migrate from hijri-converter to hijridate (#1211)
+- Fixed ClusterFuzz build error by adding dateparser.data as a binary (#1208)
+- Fix an issue detected by OSSFuzz (#1203)
+- Support two-digit years in non-Gregorian calendars (#1187)
+- Refactored CI to run extras separately and test minimum versions of dependencies, replaced flake8 with ruff, fixed tests (#1248)
+- Set minimum versions for dependencies (#1248)
+- Limited ``numpy`` to 1.x when installing ``dateparser[fasttext]`` (#1248)
+
+
+1.2.0 (2023-11-17)
+------------------
+
+New features:
+
+- New ``PREFER_MONTH_OF_YEAR`` setting (#1146)
+
+Fixes:
+
+- Absolute years in Russian are no longer being treated as a number of years in
+  the past (#1129)
+
+Cleanups and internal improvements:
+
+- Removed the use of ``datetime.utcnow``, deprecated on Python 3.12 (#1179)
+- Applied Black formatting to the code base (#1158)
+- Initial integration with OSSFuzz (#1198)
+- Extended test cases (#1191)
+
+
 1.1.8 (2023-03-22)
 ------------------
 
 Improvements:
+
 - Improved date parsing for Chinese (#1148)
 - Improved date parsing for Czech (#1151)
 - Reorder language by popularity (#1152)

{dateparser-1.1.8 → dateparser-1.2.1}/README.rst

@@ -50,7 +50,7 @@ Key Features
    locales <https://dateparser.readthedocs.io/en/latest/supported_locales.html>`__.
 -  Language autodetection
 -  Customizable behavior through
-   `settings <https://dateparser.readthedocs.io/en/latest/usage.html#settings>`__.
+   `settings <https://dateparser.readthedocs.io/en/latest/settings.html>`__.
 -  Support for `non-Gregorian calendar
    systems <https://dateparser.readthedocs.io/en/latest/introduction.html#supported-calendars>`__.
 -  Support for dates with timezones abbreviations or UTC offsets
@@ -144,8 +144,8 @@ For that reason it is important that the input is a valid date, otherwise it cou
 
 To reduce the possibility of receiving false positives, make sure that:
 
-- The input string it's a valid date and it doesn't contain any other words or numbers.
-- If you know the language or languages beforehand you add them through the ``languages`` or ``locales`` properties.
+- The input string is a valid date and doesn't contain any other words or numbers.
+- If you know the language or languages beforehand, you add them through the ``languages`` or ``locales`` properties.
 
 
 On the other hand, if you want to exclude any of the default parsers
@@ -156,7 +156,7 @@ are executed, you can do so through the
 Installation
 ------------
 
-Dateparser supports Python >= 3.7. You can install it by doing:
+Dateparser supports Python >= 3.9. You can install it by doing:
 
 ::
 
@@ -172,7 +172,7 @@ If you want to use the jalali or hijri calendar, you need to install the
 Common use cases
 ----------------
 
-**dateparser** can be used with a really different number of purposes,
+**dateparser** can be used for a wide variety of purposes,
 but it stands out when it comes to:
 
 Consuming data from different sources:
@@ -191,7 +191,7 @@ Offering natural interaction with users:
 
 -  **Tooling and CLI**: allow users to write “3 days ago” to retrieve
    information.
--  **Search engine**: allow people to search by date in an easiest /
+-  **Search engine**: allow people to search by date in an easy /
    natural format.
 -  **Bots**: allow users to interact with a bot easily
 

{dateparser-1.1.8 → dateparser-1.2.1}/dateparser/__init__.py

@@ -1,14 +1,21 @@
-__version__ = '1.1.8'
+__version__ = "1.2.1"
 
-from .date import DateDataParser
 from .conf import apply_settings
+from .date import DateDataParser
 
 _default_parser = DateDataParser()
 
 
 @apply_settings
-def parse(date_string, date_formats=None, languages=None, locales=None,
-          region=None, settings=None, detect_languages_function=None):
+def parse(
+    date_string,
+    date_formats=None,
+    languages=None,
+    locales=None,
+    region=None,
+    settings=None,
+    detect_languages_function=None,
+):
     """Parse date and time from given date string.
 
     :param date_string:
@@ -54,11 +61,22 @@ def parse(date_string, date_formats=None, languages=None, locales=None,
     """
     parser = _default_parser
 
-    if languages or locales or region or detect_languages_function or not settings._default:
-        parser = DateDataParser(languages=languages, locales=locales,
-                                region=region, settings=settings, detect_languages_function=detect_languages_function)
+    if (
+        languages
+        or locales
+        or region
+        or detect_languages_function
+        or not settings._default
+    ):
+        parser = DateDataParser(
+            languages=languages,
+            locales=locales,
+            region=region,
+            settings=settings,
+            detect_languages_function=detect_languages_function,
+        )
 
     data = parser.get_date_data(date_string, date_formats)
 
     if data:
-        return data['date_obj']
+        return data["date_obj"]

{dateparser-1.1.8 → dateparser-1.2.1}/dateparser/calendars/__init__.py

@@ -1,7 +1,8 @@
+from datetime import datetime
+
+from dateparser.conf import settings
 from dateparser.date import DateData
 from dateparser.parser import _parser
-from dateparser.conf import settings
-from datetime import datetime
 
 
 class CalendarBase:
@@ -26,7 +27,6 @@ class CalendarBase:
 
 
 class non_gregorian_parser(_parser):
-
     calendar_converter = NotImplemented
     default_year = NotImplemented
     default_month = NotImplemented
@@ -76,16 +76,20 @@ class non_gregorian_parser(_parser):
 
         return result
 
+    def handle_two_digit_year(self, year):
+        raise ValueError
+
     def _get_datetime_obj(self, **params):
-        day = params['day']
-        year = params['year']
-        month = params['month']
-        if (
-            not(0 < day <= self.calendar_converter.month_length(year, month))
-            and not(self._token_day or hasattr(self, '_token_weekday'))
+        day = params["day"]
+        year = params["year"]
+        month = params["month"]
+        if not (0 < day <= self.calendar_converter.month_length(year, month)) and not (
+            self._token_day or hasattr(self, "_token_weekday")
         ):
             day = self.calendar_converter.month_length(year, month)
-        year, month, day = self.calendar_converter.to_gregorian(year=year, month=month, day=day)
+        year, month, day = self.calendar_converter.to_gregorian(
+            year=year, month=month, day=day
+        )
         c_params = params.copy()
         c_params.update(dict(year=year, month=month, day=day))
         return datetime(**c_params)
@@ -94,12 +98,16 @@ class non_gregorian_parser(_parser):
         if not self.now:
             self._set_relative_base()
         now_year, now_month, now_day = self.calendar_converter.from_gregorian(
-            self.now.year, self.now.month, self.now.day)
+            self.now.year, self.now.month, self.now.day
+        )
         params = {
-            'day': self.day or now_day,
-            'month': self.month or now_month,
-            'year': self.year or now_year,
-            'hour': 0, 'minute': 0, 'second': 0, 'microsecond': 0,
+            "day": self.day or now_day,
+            "month": self.month or now_month,
+            "year": self.year or now_year,
+            "hour": 0,
+            "minute": 0,
+            "second": 0,
+            "microsecond": 0,
         }
         return params
 
@@ -107,26 +115,25 @@ class non_gregorian_parser(_parser):
         year, month, day = self.default_year, self.default_month, self.default_day
         token_len = len(token)
         is_digit = token.isdigit()
-        if directive == '%A' and self._weekdays and token.title() in self._weekdays:
+        if directive == "%A" and self._weekdays and token.title() in self._weekdays:
             pass
         elif (
-            directive == '%m'
-            and token_len <= 2
-            and is_digit
-            and 1 <= int(token) <= 12
+            directive == "%m" and token_len <= 2 and is_digit and 1 <= int(token) <= 12
         ):
             month = int(token)
-        elif directive == '%B' and self._months and token in self._months:
+        elif directive == "%B" and self._months and token in self._months:
             month = list(self._months.keys()).index(token) + 1
         elif (
-            directive == '%d'
+            directive == "%d"
             and token_len <= 2
             and is_digit
             and 0 < int(token) <= self.calendar_converter.month_length(year, month)
         ):
             day = int(token)
-        elif directive == '%Y' and token_len == 4 and is_digit:
+        elif directive == "%Y" and token_len == 4 and is_digit:
             year = int(token)
+        elif directive == "%Y" and token_len == 2 and is_digit:
+            year = self.handle_two_digit_year(int(token))
         else:
             raise ValueError
         return self.non_gregorian_date_cls(year, month, day)

{dateparser-1.1.8 → dateparser-1.2.1}/dateparser/calendars/hijri_parser.py

@@ -1,23 +1,22 @@
-from hijri_converter import convert
+from hijridate import Gregorian, Hijri
 
 from dateparser.calendars import non_gregorian_parser
 
 
 class hijri:
-
     @classmethod
     def to_gregorian(cls, year=None, month=None, day=None):
-        g = convert.Hijri(year=year, month=month, day=day, validate=False).to_gregorian()
+        g = Hijri(year=year, month=month, day=day, validate=False).to_gregorian()
         return g.datetuple()
 
     @classmethod
     def from_gregorian(cls, year=None, month=None, day=None):
-        h = convert.Gregorian(year, month, day).to_hijri()
+        h = Gregorian(year, month, day).to_hijri()
         return h.datetuple()
 
     @classmethod
     def month_length(cls, year, month):
-        h = convert.Hijri(year=year, month=month, day=1)
+        h = Hijri(year=year, month=month, day=1)
         return h.month_length()
 
 
@@ -35,7 +34,6 @@ class HijriDate:
 
 
 class hijri_parser(non_gregorian_parser):
-
     calendar_converter = hijri
     default_year = 1389
     default_month = 1
@@ -43,8 +41,8 @@ class hijri_parser(non_gregorian_parser):
     non_gregorian_date_cls = HijriDate
 
     _time_conventions = {
-        'am': ["صباحاً"],
-        'pm': ["مساءً"],
+        "am": ["صباحاً"],
+        "pm": ["مساءً"],
     }
 
     @classmethod
@@ -54,3 +52,9 @@ class hijri_parser(non_gregorian_parser):
             for arabic in arabics:
                 result = result.replace(arabic, latin)
         return result
+
+    def handle_two_digit_year(self, year):
+        if year >= 90:
+            return year + 1300
+        else:
+            return year + 1400

{dateparser-1.1.8 → dateparser-1.2.1}/dateparser/calendars/jalali.py

@@ -1,6 +1,7 @@
-from . import CalendarBase
 from dateparser.calendars.jalali_parser import jalali_parser
 
+from . import CalendarBase
+
 
 class JalaliCalendar(CalendarBase):
     """Calendar class for Jalali calendar."""

{dateparser-1.1.8 → dateparser-1.2.1}/dateparser/calendars/jalali_parser.py

@@ -1,10 +1,11 @@
 import re
-
-from dateparser.calendars import non_gregorian_parser
-from convertdate import persian
 from collections import OrderedDict
 from functools import reduce
 
+from convertdate import persian
+
+from dateparser.calendars import non_gregorian_parser
+
 
 class PersianDate:
     def __init__(self, year, month, day):
@@ -20,41 +21,54 @@ class PersianDate:
 
 
 class jalali_parser(non_gregorian_parser):
-
     calendar_converter = persian
     default_year = 1348
     default_month = 1
     default_day = 1
     non_gregorian_date_cls = PersianDate
 
-    _digits = {"۰": 0, "۱": 1, "۲": 2, "۳": 3, "۴": 4,
-               "۵": 5, "۶": 6, "۷": 7, "۸": 8, "۹": 9}
-
-    _months = OrderedDict([
-        # pinglish : (persian literals, month index, number of days)
-        ("Farvardin", (1, 31, ["فروردین"])),
-        ("Ordibehesht", (2, 31, ["اردیبهشت"])),
-        ("Khordad", (3, 31, ["خرداد"])),
-        ("Tir", (4, 31, ["تیر"])),
-        ("Mordad", (5, 31, ["امرداد", "مرداد"])),
-        ("Shahrivar", (6, 31, ["شهریور", "شهريور"])),
-        ("Mehr", (7, 30, ["مهر"])),
-        ("Aban", (8, 30, ["آبان"])),
-        ("Azar", (9, 30, ["آذر"])),
-        ("Dey", (10, 30, ["دی"])),
-        ("Bahman", (11, 30, ["بهمن", "بهن"])),
-        ("Esfand", (12, 29, ["اسفند"])),
-    ])
-
-    _weekdays = OrderedDict([
-        ("Sunday", ["یکشنبه"]),
-        ("Monday", ["دوشنبه"]),
-        ("Tuesday", ["سهشنبه", "سه شنبه"]),
-        ("Wednesday", ["چهارشنبه", "چهار شنبه"]),
-        ("Thursday", ["پنجشنبه", "پنج شنبه"]),
-        ("Friday", ["جمعه"]),
-        ("Saturday", ["روز شنبه", "شنبه"]),
-    ])
+    _digits = {
+        "۰": 0,
+        "۱": 1,
+        "۲": 2,
+        "۳": 3,
+        "۴": 4,
+        "۵": 5,
+        "۶": 6,
+        "۷": 7,
+        "۸": 8,
+        "۹": 9,
+    }
+
+    _months = OrderedDict(
+        [
+            # pinglish : (persian literals, month index, number of days)
+            ("Farvardin", (1, 31, ["فروردین"])),
+            ("Ordibehesht", (2, 31, ["اردیبهشت"])),
+            ("Khordad", (3, 31, ["خرداد"])),
+            ("Tir", (4, 31, ["تیر"])),
+            ("Mordad", (5, 31, ["امرداد", "مرداد"])),
+            ("Shahrivar", (6, 31, ["شهریور", "شهريور"])),
+            ("Mehr", (7, 30, ["مهر"])),
+            ("Aban", (8, 30, ["آبان"])),
+            ("Azar", (9, 30, ["آذر"])),
+            ("Dey", (10, 30, ["دی"])),
+            ("Bahman", (11, 30, ["بهمن", "بهن"])),
+            ("Esfand", (12, 29, ["اسفند"])),
+        ]
+    )
+
+    _weekdays = OrderedDict(
+        [
+            ("Sunday", ["یکشنبه"]),
+            ("Monday", ["دوشنبه"]),
+            ("Tuesday", ["سهشنبه", "سه شنبه"]),
+            ("Wednesday", ["چهارشنبه", "چهار شنبه"]),
+            ("Thursday", ["پنجشنبه", "پنج شنبه"]),
+            ("Friday", ["جمعه"]),
+            ("Saturday", ["روز شنبه", "شنبه"]),
+        ]
+    )
 
     _number_letters = {
         0: ["صفر"],
@@ -103,7 +117,10 @@ class jalali_parser(non_gregorian_parser):
         result = source
         for pers, latin in reduce(
             lambda a, b: a + b,
-            [[(value, month) for value in repl[-1]] for month, repl in cls._months.items()]
+            [
+                [(value, month) for value in repl[-1]]
+                for month, repl in cls._months.items()
+            ],
         ):
             result = result.replace(pers, latin)
         return result
@@ -113,7 +130,10 @@ class jalali_parser(non_gregorian_parser):
         result = source
         for pers, latin in reduce(
             lambda a, b: a + b,
-            [[(value, weekday) for value in repl] for weekday, repl in cls._weekdays.items()]
+            [
+                [(value, weekday) for value in repl]
+                for weekday, repl in cls._weekdays.items()
+            ],
         ):
             result = result.replace(pers, latin)
         return result
@@ -122,20 +142,23 @@ class jalali_parser(non_gregorian_parser):
     def _replace_time(cls, source):
         def only_numbers(match_obj):
             matched_string = match_obj.group()
-            return re.sub(r'\D', ' ', matched_string)
-        hour_pattern = r'ساعت\s+\d{2}'
-        minute_pattern = r'\d{2}\s+دقیقه'
-        second_pattern = r'\d{2}\s+ثانیه'
+            return re.sub(r"\D", " ", matched_string)
+
+        hour_pattern = r"ساعت\s+\d{2}"
+        minute_pattern = r"\d{2}\s+دقیقه"
+        second_pattern = r"\d{2}\s+ثانیه"
         result = re.sub(hour_pattern, only_numbers, source)
         result = re.sub(minute_pattern, only_numbers, result)
         result = re.sub(second_pattern, only_numbers, result)
-        result = re.sub(r'\s+و\s+', ':', result)
-        result = result.replace('ساعت', '')
+        result = re.sub(r"\s+و\s+", ":", result)
+        result = result.replace("ساعت", "")
         return result
 
     @classmethod
     def _replace_days(cls, source):
-        result = re.sub(r'ام|م|ین', '', source)  # removes persian variant of th/first/second/third
+        result = re.sub(
+            r"ام|م|ین", "", source
+        )  # removes persian variant of th/first/second/third
         day_pairs = list(cls._number_letters.items())
 
         def comp_key(tup):
@@ -148,7 +171,14 @@ class jalali_parser(non_gregorian_parser):
         day_pairs[1] = thirteen
 
         for persian_number, number in reduce(
-                lambda a, b: a + b,
-                [[(val, repl) for val in persian_word] for repl, persian_word in day_pairs]):
+            lambda a, b: a + b,
+            [[(val, repl) for val in persian_word] for repl, persian_word in day_pairs],
+        ):
             result = result.replace(persian_number, str(number))
         return result
+
+    def handle_two_digit_year(self, year):
+        if year > 60:
+            return year + 1300
+        else:
+            return year + 1400