dateparser 1.2.1__tar.gz → 1.2.2__tar.gz

{dateparser-1.2.1 → dateparser-1.2.2}/CONTRIBUTING.rst

@@ -179,3 +179,16 @@ Whenever the content of
 the corresponding documentation table::
 
     dateparser_scripts/update_supported_languages_and_locales.py
+
+
+Updating the Timezone Cache
+----------------------------------------------------
+
+Whenever the content of
+``dateparser/timezones.py`` is modified you need to rebuild the timezone cache.
+
+Run this command:
+``BUILD_TZ_CACHE=1 python -c "import dateparser"``
+
+which should update
+``dateparser/data/dateparser_tz_cache.pkl``

{dateparser-1.2.1 → dateparser-1.2.2}/HISTORY.rst

@@ -3,6 +3,19 @@
 History
 =======
 
+1.2.2 (2025-06-26)
+------------------
+
+Fixes:
+
+- Handle the Russian preposition “с” (#1261)
+- Fix weekday search (#1274)
+
+Improvements:
+
+- Add Python 3.14 support (#1273)
+- Cache timezone offsets to improve import time (#1250)
+
 1.2.1 (2025-02-05)
 ------------------
 

{dateparser-1.2.1 → dateparser-1.2.2}/MANIFEST.in

@@ -3,6 +3,7 @@ include CONTRIBUTING.rst
 include HISTORY.rst
 include LICENSE
 include README.rst
+include dateparser/data/dateparser_tz_cache.pkl
 include dateparser_data/settings.py
 include requirements.txt
 

{dateparser-1.2.1 → dateparser-1.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: dateparser
-Version: 1.2.1
+Version: 1.2.2
 Summary: Date parsing library designed to parse dates from HTML pages
 Home-page: https://github.com/scrapinghub/dateparser
 Author: Scrapinghub
@@ -24,7 +24,7 @@ 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: regex>=2024.9.11
 Requires-Dist: tzlocal>=0.2
 Provides-Extra: calendars
 Requires-Dist: convertdate>=2.2.1; extra == "calendars"
@@ -41,6 +41,7 @@ Dynamic: description
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: project-url
 Dynamic: provides-extra
 Dynamic: requires-dist
@@ -318,6 +319,19 @@ To be able to use them you need to install the `calendar` extra by typing:
 History
 =======
 
+1.2.2 (2025-06-26)
+------------------
+
+Fixes:
+
+- Handle the Russian preposition “с” (#1261)
+- Fix weekday search (#1274)
+
+Improvements:
+
+- Add Python 3.14 support (#1273)
+- Cache timezone offsets to improve import time (#1250)
+
 1.2.1 (2025-02-05)
 ------------------
 

{dateparser-1.2.1 → dateparser-1.2.2}/dateparser/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "1.2.1"
+__version__ = "1.2.2"
 
 from .conf import apply_settings
 from .date import DateDataParser

{dateparser-1.2.1 → dateparser-1.2.2}/dateparser/parser.py

@@ -399,8 +399,8 @@ class _parser:
             return datetime(**params)
         except ValueError as e:
             error_text = e.__str__()
-            error_msgs = ["day is out of range", "day must be in"]
-            if error_msgs[0] in error_text or error_msgs[1] in error_text:
+            error_msgs = ["day is out of range", "day must be in", "must be in range"]
+            if any(msg in error_text for msg in error_msgs):
                 if not (self._token_day or hasattr(self, "_token_weekday")):
                     # if day is not available put last day of the month
                     params["day"] = get_last_day_of_month(
@@ -512,6 +512,10 @@ class _parser:
 
             dateobj = dateobj + delta
 
+            # set the token_month here so that it is not subsequently
+            # altered by _correct_for_month
+            self._token_month = dateobj.month
+
         # NOTE: If this assert fires, self.now needs to be made offset-aware in a similar
         # way that dateobj is temporarily made offset-aware.
         assert not (self.now.tzinfo is None and dateobj.tzinfo is not None), (

{dateparser-1.2.1 → dateparser-1.2.2}/dateparser/search/__init__.py

@@ -57,6 +57,8 @@ def search_dates(
      ('on May 6th 2004', datetime.datetime(2004, 5, 6, 0, 0))]
 
     """
+    text = _search_with_detection.preprocess_text(text, languages)
+
     result = _search_with_detection.search_dates(
         text=text,
         languages=languages,

{dateparser-1.2.1 → dateparser-1.2.2}/dateparser/search/search.py

@@ -295,3 +295,10 @@ class DateSearchWithDetection:
                 language_shortname, text, settings=settings
             ),
         }
+
+    def preprocess_text(self, text, languages):
+        """Preprocess text to handle language-specific quirks."""
+        if languages and "ru" in languages:
+            # Replace "с" (from) before numbers with a placeholder
+            text = re.sub(r"\bс\s+(?=\d)", "[FROM] ", text)
+        return text

{dateparser-1.2.1 → dateparser-1.2.2}/dateparser/timezone_parser.py

@@ -1,4 +1,8 @@
+import os
+import pickle
+import zlib
 from datetime import datetime, timedelta, timezone, tzinfo
+from pathlib import Path
 
 import regex as re
 
@@ -84,8 +88,47 @@ def get_local_tz_offset():
     return offset
 
 
-_search_regex_parts = []
-_tz_offsets = list(build_tz_offsets(_search_regex_parts))
-_search_regex = re.compile("|".join(_search_regex_parts))
-_search_regex_ignorecase = re.compile("|".join(_search_regex_parts), re.IGNORECASE)
 local_tz_offset = get_local_tz_offset()
+
+_tz_offsets = None
+_search_regex = None
+_search_regex_ignorecase = None
+
+
+def _load_offsets(cache_path, current_hash):
+    global _tz_offsets, _search_regex, _search_regex_ignorecase
+
+    try:
+        with open(cache_path, mode="rb") as file:
+            (
+                serialized_hash,
+                _tz_offsets,
+                _search_regex,
+                _search_regex_ignorecase,
+            ) = pickle.load(file)
+            if current_hash is None or current_hash == serialized_hash:
+                return
+    except (FileNotFoundError, ValueError, TypeError):
+        pass
+
+    _search_regex_parts = []
+    _tz_offsets = list(build_tz_offsets(_search_regex_parts))
+    _search_regex = re.compile("|".join(_search_regex_parts))
+    _search_regex_ignorecase = re.compile("|".join(_search_regex_parts), re.IGNORECASE)
+
+    with open(cache_path, mode="wb") as file:
+        pickle.dump(
+            (current_hash, _tz_offsets, _search_regex, _search_regex_ignorecase),
+            file,
+            protocol=5,
+        )
+
+
+CACHE_PATH = Path(__file__).parent.joinpath("data", "dateparser_tz_cache.pkl")
+
+if "BUILD_TZ_CACHE" in os.environ:
+    current_hash = zlib.crc32(str(timezone_info_list).encode("utf-8"))
+else:
+    current_hash = None
+
+_load_offsets(CACHE_PATH, current_hash)

{dateparser-1.2.1 → dateparser-1.2.2}/dateparser.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: dateparser
-Version: 1.2.1
+Version: 1.2.2
 Summary: Date parsing library designed to parse dates from HTML pages
 Home-page: https://github.com/scrapinghub/dateparser
 Author: Scrapinghub
@@ -24,7 +24,7 @@ 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: regex>=2024.9.11
 Requires-Dist: tzlocal>=0.2
 Provides-Extra: calendars
 Requires-Dist: convertdate>=2.2.1; extra == "calendars"
@@ -41,6 +41,7 @@ Dynamic: description
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: project-url
 Dynamic: provides-extra
 Dynamic: requires-dist
@@ -318,6 +319,19 @@ To be able to use them you need to install the `calendar` extra by typing:
 History
 =======
 
+1.2.2 (2025-06-26)
+------------------
+
+Fixes:
+
+- Handle the Russian preposition “с” (#1261)
+- Fix weekday search (#1274)
+
+Improvements:
+
+- Add Python 3.14 support (#1273)
+- Cache timezone offsets to improve import time (#1250)
+
 1.2.1 (2025-02-05)
 ------------------
 

{dateparser-1.2.1 → dateparser-1.2.2}/dateparser.egg-info/SOURCES.txt

@@ -31,6 +31,7 @@ dateparser/custom_language_detection/fasttext.py
 dateparser/custom_language_detection/langdetect.py
 dateparser/custom_language_detection/language_mapping.py
 dateparser/data/__init__.py
+dateparser/data/dateparser_tz_cache.pkl
 dateparser/data/languages_info.py
 dateparser/data/date_translation_data/__init__.py
 dateparser/data/date_translation_data/af.py

{dateparser-1.2.1 → dateparser-1.2.2}/dateparser.egg-info/requires.txt

@@ -1,6 +1,6 @@
 python-dateutil>=2.7.0
 pytz>=2024.2
-regex!=2019.02.19,!=2021.8.27,>=2015.06.24
+regex>=2024.9.11
 tzlocal>=0.2
 
 [calendars]

{dateparser-1.2.1 → dateparser-1.2.2}/pyproject.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "1.2.1"
+current_version = "1.2.2"
 commit = true
 tag = true
 

{dateparser-1.2.1 → dateparser-1.2.2}/setup.py

@@ -31,7 +31,7 @@ setup(
     install_requires=[
         "python-dateutil>=2.7.0",
         "pytz>=2024.2",
-        "regex>=2015.06.24,!=2019.02.19,!=2021.8.27",
+        "regex>=2024.9.11",
         "tzlocal>=0.2",
     ],
     entry_points={

{dateparser-1.2.1 → dateparser-1.2.2}/tests/test_date_parser.py

@@ -628,6 +628,25 @@ class TestDateParser(BaseTestCase):
         self.then_date_was_parsed_by_date_parser()
         self.then_date_obj_exactly_is(expected)
 
+    @parameterized.expand(
+        [
+            param("Monday", datetime(2015, 3, 2)),
+        ]
+    )
+    def test_preferably_future_dates_relative_last_week_of_month(
+        self, date_string, expected
+    ):
+        self.given_local_tz_offset(0)
+        self.given_parser(
+            settings={
+                "PREFER_DATES_FROM": "future",
+                "RELATIVE_BASE": datetime(2015, 2, 24, 15, 30),
+            }
+        )
+        self.when_date_is_parsed(date_string)
+        self.then_date_was_parsed_by_date_parser()
+        self.then_date_obj_exactly_is(expected)
+
     @parameterized.expand(
         [
             param("10 December", datetime(2015, 12, 10)),
@@ -875,7 +894,7 @@ class TestDateParser(BaseTestCase):
     ):
         self.when_date_is_parsed_by_date_parser(date_string)
         self.then_error_was_raised(
-            ValueError, ["day is out of range for month", message]
+            ValueError, ["day is out of range for month", "must be in range", message]
         )
 
     @parameterized.expand(

{dateparser-1.2.1 → dateparser-1.2.2}/tests/test_search.py

@@ -410,7 +410,7 @@ class TestTranslateSearch(BaseTestCase):
                 "Die UdSSR blieb gemäß dem Neutralitätspakt "
                 "vom 13. April 1941 gegenüber Japan vorerst neutral.",
                 [
-                    ("Die", datetime.datetime(1999, 1, 28, 0, 0)),
+                    ("Die", datetime.datetime(1999, 12, 28, 0, 0)),
                     ("13. April 1941", datetime.datetime(1941, 4, 13, 0, 0)),
                 ],
                 settings={"RELATIVE_BASE": datetime.datetime(2000, 1, 1)},
@@ -1090,3 +1090,16 @@ class TestTranslateSearch(BaseTestCase):
             text=text, languages=languages, error_type=ValueError
         )
         self.check_error_message("Unknown language(s): 'unknown language code'")
+
+    def test_search_dates_with_prepositions(self):
+        """Test `search_dates` for parsing Russian date ranges with prepositions and language detection."""
+        result = search_dates(
+            "Сервис будет недоступен с 12 января по 30 апреля.",
+            add_detected_language=True,
+            languages=["ru"],
+        )
+        expected = [
+            ("12 января", datetime.datetime(2025, 1, 12, 0, 0), "ru"),
+            ("30 апреля", datetime.datetime(2025, 4, 30, 0, 0), "ru"),
+        ]
+        assert result == expected