dateparser 1.2.1__py3-none-any.whl → 1.3.0__py3-none-any.whl

dateparser/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "1.2.1"
+__version__ = "1.3.0"
 
 from .conf import apply_settings
 from .date import DateDataParser

dateparser/conf.py

@@ -27,6 +27,9 @@ class Settings:
     * `SKIP_TOKENS`
     * `NORMALIZE`
     * `RETURN_TIME_AS_PERIOD`
+    * `RETURN_TIME_SPAN`
+    * `DEFAULT_START_OF_WEEK`
+    * `DEFAULT_DAYS_IN_MONTH`
     * `PARSERS`
     * `DEFAULT_LANGUAGES`
     * `LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD`
@@ -229,6 +232,14 @@ def check_settings(settings):
         "CACHE_SIZE_LIMIT": {
             "type": int,
         },
+        "RETURN_TIME_SPAN": {"type": bool},
+        "DEFAULT_START_OF_WEEK": {
+            "values": ("monday", "sunday"),
+            "type": str,
+        },
+        "DEFAULT_DAYS_IN_MONTH": {
+            "type": int,
+        },
     }
 
     modified_settings = settings._mod_settings  # check only modified settings

dateparser/data/date_translation_data/en.py

@@ -51,32 +51,39 @@ info = {
     ],
     "monday": [
         "mon",
-        "monday"
+        "monday",
+        "mo"
     ],
     "tuesday": [
         "tue",
         "tuesday",
+        "tu",
         "Tues"
     ],
     "wednesday": [
         "wed",
-        "wednesday"
+        "wednesday",
+        "we"
     ],
     "thursday": [
         "thu",
-        "thursday"
+        "thursday",
+        "th"
     ],
     "friday": [
         "fri",
-        "friday"
+        "friday",
+        "fr"
     ],
     "saturday": [
         "sat",
-        "saturday"
+        "saturday",
+        "sa"
     ],
     "sunday": [
         "sun",
-        "sunday"
+        "sunday",
+        "su"
     ],
     "am": [
         "am"
@@ -258,6 +265,8 @@ info = {
         "in \\1 week": [
             "in (\\d+[.,]?\\d*) week",
             "in (\\d+[.,]?\\d*) weeks",
+            "in (\\d+[.,]?\\d*) weeks time",
+            "in (\\d+[.,]?\\d*) weeks' time",
             "in (\\d+[.,]?\\d*) wk"
         ],
         "in \\1 year": [

dateparser/data/date_translation_data/fi.py

@@ -316,6 +316,7 @@ info = {
     "locale_specific": {},
     "skip": [
         ":n",
+        "klo",
         " ",
         "'",
         ",",

dateparser/data/date_translation_data/ru.py

@@ -340,73 +340,91 @@ info = {
     ],
     "simplifications": [
         {
-            "од(на|ну|ни|ной|ин)": "1"
+            "од(ин|на|ну|ни|ной|ною|но|ного|ному|ним|нем)": "1"
         },
         {
-            "дв(а|е|ое|ух)": "2"
+            "перв(ой|ого|ому|ым|ом|ая|ую|ое|ые|ых|ыми)": "1"
         },
         {
-            "пар[ауы]": "2"
+            "дв(а|е|ух|ум|умя|ое)": "2"
         },
         {
-            "три": "3"
+            "пар(а|ы|е|у|ой|ою|ам|ами|ах)": "2"
         },
         {
-            "четыре": "4"
+            "втор(ой|ого|ому|ым|ом|ая|ую|ое|ые|ых|ыми)": "2"
         },
         {
-            "пять": "5"
+            "тр(и|ёх|ем|ём|емя|етье)": "3"
         },
         {
-            "шесть": "6"
+            "трети(й|его|ему|им|ем|я|ей|ею|ую|е|и|их|ими)": "3"
         },
         {
-            "семь": "7"
+            "четыр(е|ёх|ем|ём|ьмя)": "4"
         },
         {
-            "восемь": "8"
+            "четвёрт(ый|ого|ому|ым|ом|ая|ой|ою|ую|ое|ые|ых|ыми)": "4"
         },
         {
-            "девять": "9"
+            "четверт(ый|ого|ому|ым|ом|ая|ой|ою|ую|ое|ые|ых|ыми)": "4"
         },
         {
-            "десять": "10"
+            "пят(ь|и|ью)": "5"
         },
         {
-            "одиннадцать": "11"
+            "пят(ый|ого|ому|ым|ом|ая|ой|ою|ую|ое|ые|ых|ыми)": "5"
         },
         {
-            "двенадцать": "12"
+            "шест(ь|и|ью)": "6"
         },
         {
-            "пятнадцать": "15"
+            "шест(ый|ого|ому|ым|ом|ая|ой|ою|ую|ое|ые|ых|ыми)": "6"
         },
         {
-            "двадцать": "20"
+            "сем(ь|и|ью)": "7"
         },
         {
-            "тридцать": "30"
+            "седьм(ой|ого|ому|ым|ом|ая|ой|ою|ую|ое|ые|ых|ыми)": "7"
         },
         {
-            "сорок": "40"
+            "восьм(и|ью|ьею)|восем(ь|ью)": "8"
         },
         {
-            "пятьдесят": "50"
+            "восьм(ой|ого|ому|ым|ом|ая|ой|ою|ую|ое|ые|ых|ыми)": "8"
         },
         {
-            "несколько секунд": "44 секунды"
+            "девят(ь|и|ью)": "9"
         },
         {
-            "полчаса": "30 минут"
+            "девят(ый|ого|ому|ым|ом|ая|ой|ою|ую|ое|ые|ых|ыми)": "9"
         },
         {
-            "полгода": "6 месяцев"
+            "десять": "10"
         },
         {
-            "полтора часа": "90 минут"
+            "одиннадцать": "11"
         },
         {
-            "полтора года": "18 месяцев"
+            "двенадцать": "12"
+        },
+        {
+            "пятнадцать": "15"
+        },
+        {
+            "двадцат(ь|ое)": "20"
+        },
+        {
+            "тридцат(ь|ое)": "30"
+        },
+        {
+            "соро(к|ка|ковое)": "40"
+        },
+        {
+            "пятьдесят": "50"
+        },
+        {
+            "пятидесятое": "50"
         },
         {
             "((?<=(через|спустя|в течение)\\s+)секунд[уы]|(?<=[^\\d]\\s+|^)секунду(?=(\\s+назад)))": "1 секунду"
@@ -426,12 +444,27 @@ info = {
         {
             "((?<=(через|спустя|в течение)\\s+)недел[юи]|(?<=[^\\d]\\s+|^)неделю(?=(\\s+назад)))": "1 неделю"
         },
+        {
+            "полгода": "6 месяцев"
+        },
         {
             "((?<=(через|спустя|в течение)\\s+)месяца?|(?<=[^\\d]\\s+|^)месяц(?=(\\s+назад)))": "1 месяц"
         },
         {
             "((?<=(через|спустя|в течение)\\s+)года?|(?<=[^\\d]\\s+|^)год(?=(\\s+назад)))": "1 год"
         },
+        {
+            "полтора года": "18 месяцев"
+        },
+        {
+            "полчаса": "30 минут"
+        },
+        {
+            "несколько секунд": "44 секунды"
+        },
+        {
+            "полтора часа": "90 минут"
+        },
         {
             "(\\d{3,}1)\\s*год\\s*$": "\\1"
         },

dateparser/date.py

@@ -19,6 +19,7 @@ from dateparser.utils import (
     set_correct_day_from_settings,
     set_correct_month_from_settings,
 )
+from dateparser.utils.strptime import strptime as patched_strptime
 
 APOSTROPHE_LOOK_ALIKE_CHARS = [
     "\N{RIGHT SINGLE QUOTATION MARK}",  # '\u2019'
@@ -182,7 +183,7 @@ def parse_with_formats(date_string, date_formats, settings):
     period = "day"
     for date_format in date_formats:
         try:
-            date_obj = datetime.strptime(date_string, date_format)
+            date_obj = patched_strptime(date_string, date_format)
         except ValueError:
             continue
         else:

dateparser/freshness_date_parser.py

@@ -10,7 +10,7 @@ from .parser import time_parser
 from .timezone_parser import pop_tz_offset_from_string
 
 _UNITS = r"decade|year|month|week|day|hour|minute|second"
-PATTERN = re.compile(r"(\d+[.,]?\d*)\s*(%s)\b" % _UNITS, re.I | re.S | re.U)
+PATTERN = re.compile(r"([+-]?\d+[.,]?\d*)\s*(%s)\b" % _UNITS, re.I | re.S | re.U)
 
 
 class FreshnessDateDataParser:
@@ -112,7 +112,13 @@ class FreshnessDateDataParser:
         if not self._are_all_words_units(date_string):
             return None, None
 
-        kwargs = self.get_kwargs(date_string)
+        result = self.get_kwargs(date_string)
+        if isinstance(result, tuple):
+            kwargs, explicit_signs = result
+        else:
+            kwargs = result
+            explicit_signs = {}
+
         if not kwargs:
             return None, None
         period = "day"
@@ -121,16 +127,27 @@ class FreshnessDateDataParser:
                 if k in kwargs:
                     period = k[:-1]
                     break
-        td = relativedelta(**kwargs)
 
-        if (
+        going_forward = (
             re.search(r"\bin\b", date_string)
             or re.search(r"\bfuture\b", prefer_dates_from)
             and not re.search(r"\bago\b", date_string)
-        ):
-            date = now + td
-        else:
-            date = now - td
+        )
+
+        adjusted_kwargs = {}
+        for key, value in kwargs.items():
+            if explicit_signs.get(key, False):
+                adjusted_kwargs[key] = value
+            else:
+                if going_forward:
+                    adjusted_kwargs[key] = value
+                else:
+                    adjusted_kwargs[key] = -value
+
+        td = relativedelta(**adjusted_kwargs)
+
+        date = now + td
+
         return date, period
 
     def get_kwargs(self, date_string):
@@ -139,12 +156,21 @@ class FreshnessDateDataParser:
             return {}
 
         kwargs = {}
+        explicit_signs = {}
+
         for num, unit in m:
+            has_explicit_sign = num.startswith("+") or num.startswith("-")
+            explicit_signs[unit + "s"] = has_explicit_sign
             kwargs[unit + "s"] = float(num.replace(",", "."))
+
         if "decades" in kwargs:
             kwargs["years"] = 10 * kwargs["decades"] + kwargs.get("years", 0)
+            if "decades" in explicit_signs:
+                explicit_signs["years"] = explicit_signs["decades"]
             del kwargs["decades"]
-        return kwargs
+            explicit_signs.pop("decades", None)
+
+        return kwargs, explicit_signs
 
     def get_date_data(self, date_string, settings=None):
         from dateparser.date import DateData

dateparser/languages/dictionary.py

@@ -201,14 +201,25 @@ class Dictionary:
                 curr_split = (
                     [known] if self._should_capture(known, keep_formatting) else []
                 )
+
                 if unparsed and self._should_capture(unparsed, keep_formatting):
                     curr_split = (
                         self._split_by_numerals(unparsed, keep_formatting) + curr_split
                     )
+
                 if unknown:
                     string = unknown if string != unknown else ""
 
-            splitted.extend(curr_split)
+            for token in curr_split:
+                if (
+                    splitted
+                    and splitted[-1].isdigit()
+                    and token in {"st", "nd", "rd", "th"}
+                ):
+                    continue
+
+                splitted.append(token)
+
         return splitted
 
     def _split_by_numerals(self, string, keep_formatting):

dateparser/languages/locale.py

@@ -144,7 +144,6 @@ class Locale:
                     date_string_tokens[i] = dictionary[word] or fallback
         if "in" in date_string_tokens:
             date_string_tokens = self._clear_future_words(date_string_tokens)
-
         return self._join(
             list(filter(bool, date_string_tokens)),
             separator="" if keep_formatting else " ",
@@ -426,11 +425,39 @@ class Locale:
     def _simplify(self, date_string, settings=None):
         date_string = date_string.lower()
         simplifications = self._get_simplifications(settings=settings)
+
+        if self.info.get("name") == "ru":
+            date_string = self._process_russian_compound_ordinals(
+                date_string, simplifications
+            )
+        else:
+            date_string = self._apply_simplifications(date_string, simplifications)
+
+        return date_string
+
+    def _apply_simplifications(self, date_string, simplifications):
         for simplification in simplifications:
             pattern, replacement = list(simplification.items())[0]
             date_string = pattern.sub(replacement, date_string).lower()
         return date_string
 
+    def _process_russian_compound_ordinals(self, date_string, simplifications):
+        """Process Russian compound ordinals mathematically (двадцать + первое = 21)."""
+        date_string = self._apply_simplifications(date_string, simplifications)
+
+        def replace_number_pairs(match):
+            first_num = int(match.group(1))
+            second_num = int(match.group(2))
+            result = first_num + second_num
+            if 1 <= result <= 31 and first_num in [20, 30] and 1 <= second_num <= 9:
+                return str(result)
+            return match.group(0)
+
+        number_pair_pattern = r"\b(\d+)\s+(\d+)\b"
+        date_string = re.sub(number_pair_pattern, replace_number_pairs, date_string)
+
+        return date_string
+
     def _get_simplifications(self, settings=None):
         no_word_spacing = eval(self.info.get("no_word_spacing", "False"))
         if settings.NORMALIZE:

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/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/search/search.py

@@ -1,4 +1,5 @@
 from collections.abc import Set
+from datetime import datetime
 
 import regex as re
 
@@ -7,6 +8,7 @@ from dateparser.custom_language_detection.language_mapping import map_languages
 from dateparser.date import DateDataParser
 from dateparser.languages.loader import LocaleDataLoader
 from dateparser.search.text_detection import FullTextLanguageDetector
+from dateparser.utils.time_spans import detect_time_span, generate_time_span
 
 RELATIVE_REG = re.compile("(ago|in|from now|tomorrow|today|yesterday)")
 
@@ -185,8 +187,23 @@ class _ExactLanguageSearch:
             translated=translated,
             settings=settings,
         )
+
+        results = list(zip(substrings, [i[0]["date_obj"] for i in parsed]))
+
+        if getattr(settings, "RETURN_TIME_SPAN", False):
+            span_info = detect_time_span(text)
+            if span_info:
+                base_date = getattr(settings, "RELATIVE_BASE", None) or datetime.now()
+                start_date, end_date = generate_time_span(
+                    span_info, base_date, settings
+                )
+
+                matched_text = span_info["matched_text"]
+                results.append((matched_text + " (start)", start_date))
+                results.append((matched_text + " (end)", end_date))
+
         parser._settings = Settings()
-        return list(zip(substrings, [i[0]["date_obj"] for i in parsed]))
+        return results
 
 
 class DateSearchWithDetection:
@@ -295,3 +312,10 @@ 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/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/utils/strptime.py

@@ -90,7 +90,34 @@ def patch_strptime():
 __strptime = patch_strptime()
 
 
-def strptime(date_string, format):
+def _prepare_format(date_string: str, og_format: str) -> tuple[str, str]:
+    # Adapted from std lib: https://github.com/python/cpython/blob/e34a5e33049ce845de646cf24a498766a2da3586/Lib/_strptime.py#L448
+    format = re.sub(r"([\\.^$*+?\(\){}\[\]|])", r"\\\1", og_format)
+    format = re.sub(r"\s+", r"\\s+", format)
+    format = re.sub(r"'", "['\u02bc]", format)
+    year_in_format = False
+    day_of_month_in_format = False
+
+    def repl(m: re.Match[str]) -> str:
+        format_char = m[1]
+        if format_char in ("Y", "y", "G"):
+            nonlocal year_in_format
+            year_in_format = True
+        elif format_char in ("d",):
+            nonlocal day_of_month_in_format
+            day_of_month_in_format = True
+
+        return ""
+
+    _ = re.sub(r"%[-_0^#]*[0-9]*([OE]?\\?.?)", repl, format)
+    if day_of_month_in_format and not year_in_format:
+        current_year = datetime.today().year
+        return f"{current_year} {date_string}", f"%Y {og_format}"
+    return date_string, og_format
+
+
+def strptime(date_string: str, format: str) -> datetime:
+    date_string, format = _prepare_format(date_string, format)
     obj = datetime(*__strptime(date_string, format)[:-3])
 
     if "%f" in format:

dateparser/utils/time_spans.py

@@ -0,0 +1,152 @@
+"""
+Utilities for handling time spans and date ranges.
+"""
+
+import re
+from datetime import datetime, timedelta
+from dateutil.relativedelta import relativedelta
+
+
+def get_week_start(date, start_of_week="monday"):
+    """Get the start of the week for a given date."""
+    if start_of_week == "monday":
+        days_back = date.weekday()
+    else:  # sunday
+        days_back = (date.weekday() + 1) % 7
+
+    return date - timedelta(days=days_back)
+
+
+def get_week_end(date, start_of_week="monday"):
+    """Get the end of the week for a given date."""
+    week_start = get_week_start(date, start_of_week)
+    return week_start + timedelta(days=6)
+
+
+def detect_time_span(text):
+    """Detect time span expressions in text and return span information."""
+    span_patterns = [
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:past|last|previous)\s+month\b",
+            "type": "month",
+            "direction": "past",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:past|last|previous)\s+week\b",
+            "type": "week",
+            "direction": "past",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:past|last|previous)\s+(\d+)\s+days?\b",
+            "type": "days",
+            "direction": "past",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:past|last|previous)\s+(\d+)\s+weeks?\b",
+            "type": "weeks",
+            "direction": "past",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:past|last|previous)\s+(\d+)\s+months?\b",
+            "type": "months",
+            "direction": "past",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:next|coming|following)\s+month\b",
+            "type": "month",
+            "direction": "future",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:next|coming|following)\s+week\b",
+            "type": "week",
+            "direction": "future",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:next|coming|following)\s+(\d+)\s+days?\b",
+            "type": "days",
+            "direction": "future",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:next|coming|following)\s+(\d+)\s+weeks?\b",
+            "type": "weeks",
+            "direction": "future",
+        },
+        {
+            "pattern": r"\b(?:for\s+the\s+|during\s+the\s+|in\s+the\s+)?(?:next|coming|following)\s+(\d+)\s+months?\b",
+            "type": "months",
+            "direction": "future",
+        },
+    ]
+
+    for pattern_info in span_patterns:
+        match = re.search(pattern_info["pattern"], text, re.IGNORECASE)
+        if match:
+            result = {
+                "type": pattern_info["type"],
+                "direction": pattern_info["direction"],
+                "matched_text": match.group(0),
+                "start_pos": match.start(),
+                "end_pos": match.end(),
+            }
+
+            if match.groups():
+                result["number"] = int(match.group(1))
+
+            return result
+
+    return None
+
+
+def generate_time_span(span_info, base_date=None, settings=None):
+    """Generate start and end dates for a time span."""
+    if base_date is None:
+        base_date = datetime.now()
+
+    if settings is None:
+        start_of_week = "monday"
+        days_in_month = 30
+    else:
+        start_of_week = getattr(settings, "DEFAULT_START_OF_WEEK", "monday")
+        days_in_month = getattr(settings, "DEFAULT_DAYS_IN_MONTH", 30)
+
+    span_type = span_info["type"]
+    direction = span_info["direction"]
+    number = span_info.get("number", 1)
+
+    if direction == "past":
+        end_date = base_date
+
+        if span_type == "month":
+            start_date = end_date - relativedelta(days=days_in_month)
+        elif span_type == "week":
+            week_start = get_week_start(end_date, start_of_week)
+            start_date = week_start - timedelta(days=7)
+            end_date = week_start - timedelta(days=1)
+        elif span_type == "days":
+            start_date = end_date - timedelta(days=number)
+        elif span_type == "weeks":
+            start_date = end_date - timedelta(weeks=number)
+        elif span_type == "months":
+            start_date = end_date - relativedelta(months=number)
+        else:
+            start_date = end_date - timedelta(days=1)
+
+    else:
+        start_date = base_date
+
+        if span_type == "month":
+            end_date = start_date + relativedelta(days=days_in_month)
+        elif span_type == "week":
+            week_start = get_week_start(start_date, start_of_week)
+            start_date = week_start + timedelta(days=7)
+            end_date = start_date + timedelta(days=6)
+        elif span_type == "days":
+            end_date = start_date + timedelta(days=number)
+        elif span_type == "weeks":
+            end_date = start_date + timedelta(weeks=number)
+        elif span_type == "months":
+            end_date = start_date + relativedelta(months=number)
+        else:
+            end_date = start_date + timedelta(days=1)
+
+    return (start_date, end_date)

{dateparser-1.2.1.dist-info → dateparser-1.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: dateparser
-Version: 1.2.1
+Version: 1.3.0
 Summary: Date parsing library designed to parse dates from HTML pages
 Home-page: https://github.com/scrapinghub/dateparser
 Author: Scrapinghub
@@ -13,25 +13,25 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: BSD License
 Classifier: Natural Language :: English
 Classifier: Programming Language :: Python :: 3
-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 :: 3.14
 Classifier: Programming Language :: Python :: Implementation :: CPython
-Requires-Python: >=3.8
+Requires-Python: >=3.10
 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"
 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"
+Requires-Dist: numpy<2,>=1.22.0; extra == "fasttext"
 Provides-Extra: langdetect
 Requires-Dist: langdetect>=1.0.0; extra == "langdetect"
 Dynamic: author
@@ -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
@@ -260,6 +261,17 @@ You can extract dates from longer strings of text. They are returned as list of
    
    :noindex:
 
+Time Span Detection
+-------------------
+
+The `search_dates` function can detect time spans from expressions like "past month", "last week", etc. When `RETURN_TIME_SPAN` is enabled, it returns start and end dates for the detected period.
+
+.. code-block:: python
+
+    >>> search_dates("Messages from the past month", settings={'RETURN_TIME_SPAN': True})
+    [('past month (start)', datetime.datetime(2024, 11, 7, 0, 0)), 
+     ('past month (end)', datetime.datetime(2024, 12, 7, 23, 59, 59, 999999))]
+
 Advanced Usage
 ==============
 If you need more control over what is being parser check the `settings` section as well as the `using-datedataparser` section.
@@ -318,6 +330,44 @@ To be able to use them you need to install the `calendar` extra by typing:
 History
 =======
 
+1.3.0 (2026-02-04)
+------------------
+
+Dropped Python 3.9 support. (#1296)
+
+New features:
+
+- ``search_dates()`` can now detect time spans from expressions like “past
+  month”, “last week”, etc. For details, see the “Time Span Detection” section
+  and the ``RETURN_TIME_SPAN``, ``DEFAULT_START_OF_WEEK`` and
+  ``DEFAULT_DAYS_IN_MONTH`` settings in the documentation. (#1284)
+
+Fixes:
+
+- Assume the current year if not specified (#1288)
+- Support expressions like “yesterday +1h” (#1303)
+- English: Support most 2-letter day-of-the-week names (#1214)
+- English: Support “in N weeks' time” (#1283)
+- Finnish: Support dates with “klo” (#1301)
+- Russian: Support compound ordinals (#1280)
+
+Cleanups and internal improvements:
+
+- Fixed year expectation issues in tests. (#1294)
+
+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.dist-info → dateparser-1.3.0.dist-info}/RECORD

@@ -1,10 +1,10 @@
-dateparser/__init__.py,sha256=3ajvpKU-xlhD0gF4Xp1bqU3PGTrMFLfYBlua29tRM1Q,2739
-dateparser/conf.py,sha256=ynrRajwQ6dtgbSm9T0plfxQEYEarHo6Qsr76ISInX-4,8467
-dateparser/date.py,sha256=AluFz3-uzuRL6Y1cF5uFgjpcxEmTspJAHGMdIR1oBzE,21763
+dateparser/__init__.py,sha256=E93qThUWMzU0u_HUYzn6LIueEYKO_KmqGbX27D3xz_s,2739
+dateparser/conf.py,sha256=bpJiegIAnBPXoPhtEe5GN2Vf6XgWiqyJ76WPYGL_DCs,8782
+dateparser/date.py,sha256=DZZZ04Csp5psRxVA3Pmu7BEyTV5549IxSi-bnDEv4wc,21829
 dateparser/date_parser.py,sha256=LPMD1La3fUTyfa17i0Ng-mii6ucWIBme-zJJY3es-Ug,1782
-dateparser/freshness_date_parser.py,sha256=VgFAxveZqRDXCHTkQzTab7jx197btjv-YFcSOeZwOAY,5081
-dateparser/parser.py,sha256=_PiRb9uoIQNcnymsd0KRO6ZO5M_82Aa418rwp-PHGKU,25838
-dateparser/timezone_parser.py,sha256=98cWyyBl8D71Ry-cAVgB0pa935NPHZQiP451YLvK_zU,2913
+dateparser/freshness_date_parser.py,sha256=0E8zbvHt_zA97Fdet3HUHk8tXtVEzBH-f0Yi_Vt-Z44,5899
+dateparser/parser.py,sha256=KDde8HlyD5wFERiT8ABrIxTakLsEE7VYA4Kif6VWRbQ,26005
+dateparser/timezone_parser.py,sha256=MoMTAH__hkeaoZQ6VaZhJpUPxd-yA9QTczm-mmHztKc,4042
 dateparser/timezones.py,sha256=gtJhZDCy4sw37MpUogWk4LHKmn8DpG5caO3LIaCC264,13981
 dateparser/calendars/__init__.py,sha256=Gf9qLl9xbCFhmuWtuakkaHy_vSuOLOoo1kr33xJGkIY,4323
 dateparser/calendars/hijri.py,sha256=J9IUHs162UslQ4r5OPIr-BgmiyY3_4kj_z1wOIlB57E,168
@@ -16,6 +16,7 @@ dateparser/custom_language_detection/fasttext.py,sha256=uuNN8JlKcUSi5pqUrnywPRrq
 dateparser/custom_language_detection/langdetect.py,sha256=lxSrW6bpB3f4_YaF3nnyi6xmSsvwsnmBmOelHQGKeck,1195
 dateparser/custom_language_detection/language_mapping.py,sha256=HeZLw65ghqXmjLaE8KEOm4BZedkFVrX7dvC_FynXWtk,557
 dateparser/data/__init__.py,sha256=20PfpbkZv8Q9LU6p0T4RA0YNq8oQykhvWThKPhYgp6Y,115
+dateparser/data/dateparser_tz_cache.pkl,sha256=wXxZFkophi11wLJJdVEgUgLpcqf1GS5SAA89e8Mg0-I,134536
 dateparser/data/languages_info.py,sha256=BPHjASz2MUvgc7kF2uXrtYbcj823kjLxrR8X_wLiAEc,13406
 dateparser/data/date_translation_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dateparser/data/date_translation_data/af.py,sha256=LR5yRcwOJ9_QWn5EH_jwfAhwNGtnf4RFhdNoVHqjd7U,4588
@@ -60,7 +61,7 @@ dateparser/data/date_translation_data/dz.py,sha256=Tnpiobh5Z0B-ypBu8iwFnoKETeDbi
 dateparser/data/date_translation_data/ebu.py,sha256=urgcEcGO18BZI9yL9VoNvrpnPiIwzpdp2Lu_gaULCpg,2708
 dateparser/data/date_translation_data/ee.py,sha256=9iFh_krQjTdG7wHb0F-mHV1M9tNIVY_ZvXFElo8JsTM,4693
 dateparser/data/date_translation_data/el.py,sha256=ZLpqqIxH1dHAh9R74Nc1u2fFj076H92VpbnoBSaFH5g,6726
-dateparser/data/date_translation_data/en.py,sha256=T4q6ob31BAwZ3uMMrgmYzZ7n8SwRE40DlWndYGxrTOg,18292
+dateparser/data/date_translation_data/en.py,sha256=xEwkpuITw596WymLZVJgHW4TKjzpY2xs2hMZBhTh-Uk,18481
 dateparser/data/date_translation_data/eo.py,sha256=zRsL-WwsirzvOa1egdLX2eYSJcBLLSqf9_kFHRCq4iM,2555
 dateparser/data/date_translation_data/es.py,sha256=jHUrQVXJJr5aJDEJ2_m14QEwjgXRIW8PyOjahBcGMg4,10564
 dateparser/data/date_translation_data/et.py,sha256=32v713IxqOn6tylqQM2PF533cEIB8WdaDvhXj7NmWQk,4471
@@ -68,7 +69,7 @@ dateparser/data/date_translation_data/eu.py,sha256=q2ozI0EjZ15OgL9XDZwSK3SBzuLGZ
 dateparser/data/date_translation_data/ewo.py,sha256=91HMITP1VhKEOkCcUlcH_IoQId_1N1ubToPKHAUaI34,2738
 dateparser/data/date_translation_data/fa.py,sha256=ubYX0IR-kNqg2FcfbwU-fk9MZcm-_aSULd1GzEX_fdo,5315
 dateparser/data/date_translation_data/ff.py,sha256=gm3_z4qoVSMAOMVJFQPyu_WscLmuj89t4e6lfD_UrkU,2750
-dateparser/data/date_translation_data/fi.py,sha256=4JE041V8liwTWjy6hLR251uWUAsPzOwRnf0C1bBAbvE,7119
+dateparser/data/date_translation_data/fi.py,sha256=gh5OM8sBw3AoocrXINweOJzQp11CM39FHjKIqyA-2uU,7134
 dateparser/data/date_translation_data/fil.py,sha256=rEf4yjFoKDDZUGjEXfscBiA51D_P30KLHgs2lHdlE2M,4160
 dateparser/data/date_translation_data/fo.py,sha256=q0UZ1nf0E9r0LNeZxh6YmeBVFNQ3lnQ1_W-J1mjuCvo,5163
 dateparser/data/date_translation_data/fr.py,sha256=CrfovpWkbm24zo4Cx6mBTG10rMg570Vldf22BGFbV5U,10219
@@ -168,7 +169,7 @@ dateparser/data/date_translation_data/rm.py,sha256=XR9vQVtjdmYAO3CF1HZ3geg9ss9w8
 dateparser/data/date_translation_data/rn.py,sha256=m8C0_pWqKSfSP6cEX7W7qFLDRBT0_3CMBpjihCmj878,2636
 dateparser/data/date_translation_data/ro.py,sha256=BmIeWoTCSj2_Jm7tSSW576KihgeKL4ZbLYDm3c8VXtw,5407
 dateparser/data/date_translation_data/rof.py,sha256=6P8K_OTRvB3l_uJNPbqMDhcugd9-04LOixoJCEmFCSg,2501
-dateparser/data/date_translation_data/ru.py,sha256=wrH4DQmhqi2h9dFB7iKykWV1vLJBDX07VoBXtgcGl2M,10690
+dateparser/data/date_translation_data/ru.py,sha256=Mn08V6pMrwrtp7XMFUATHJR92Nj5nSJ-kpbSof5OFQ4,12205
 dateparser/data/date_translation_data/rw.py,sha256=WcS5199LBbHjaewoQunQg-4fj8tlzuAw0yUkzQ4ciS0,2597
 dateparser/data/date_translation_data/rwk.py,sha256=iom2uEfZDe-UORTeggcIyTlaGH7JR0EDkZjD_eTfuvc,2551
 dateparser/data/date_translation_data/sah.py,sha256=xLH9m4W8DT7-HmS8LW0WS40yIRg-aV5pcU3lvdW2sCA,4536
@@ -224,33 +225,34 @@ dateparser/data/date_translation_data/zh-Hant.py,sha256=3QH9WURGtqTWG4E6sUlCogoa
 dateparser/data/date_translation_data/zh.py,sha256=jTbrYZtOGx19fPgkH-3ccYUkdb-pqaayNwr6R5SB8FE,5318
 dateparser/data/date_translation_data/zu.py,sha256=blFaRxCN2KVqzAi_7NP5cf_Xz_gAX4YqAOkn1nyZDBg,3467
 dateparser/languages/__init__.py,sha256=iQ4o11LbvlawSaAzPHRuavXqDmzPdTmSgI_YwUTgQ9A,62
-dateparser/languages/dictionary.py,sha256=KiSswl08OsBqW-UiBeST2ff-BtqZyH-sNy1FAsFXjxo,11875
+dateparser/languages/dictionary.py,sha256=h7Sp_lYYuVdMCeSdz7fkmav8trRFQueQtSiS4kHt3xk,12118
 dateparser/languages/loader.py,sha256=gTyyVEX8ppeVEQ1SrIjjxwSq8hpTI5HTnS_cyVotegc,7323
-dateparser/languages/locale.py,sha256=3T5VIzS5WHpcs7fScKW-rQiW4refCBrp-BxyXzDYlio,24631
+dateparser/languages/locale.py,sha256=khMelzkzLcTH7yF01W9ksJoIPcm72IBvhUTVN5yQE70,25752
 dateparser/languages/validation.py,sha256=gtLpxvh3XI_nzryBZ8NA6QL8YLcT6HV1j81dV3nDxY4,16750
-dateparser/search/__init__.py,sha256=__laR2Q19meiPpZLILINZMePGRG4DmvOoc2tOncU9ZM,2841
+dateparser/search/__init__.py,sha256=4AixzJu9YID1vzNSKx8uJ0cyKNZGvO8BzMN6Jpoci84,2909
 dateparser/search/detection.py,sha256=YAnTYbM18FGZV2pxn6lNDbfoiQttzM52ZDgOhlV87II,2695
-dateparser/search/search.py,sha256=-c9LIBUnTPRfchEoFrcVeu5JVJBkMsl1jGueB3FhKKY,11846
+dateparser/search/search.py,sha256=_hrGubK6sFk-1zwAeRo_dkqniakL6qJOI-nhUhOQivw,12833
 dateparser/search/text_detection.py,sha256=SSQUOr5V3Qm946Tiz7hNWcpYJtcyP9Bxayxec0hC7zc,3238
 dateparser/utils/__init__.py,sha256=X5ssdQuo60F_SnVcKpt-a2ehvPClMaX2pQ2vwGWGSac,7234
-dateparser/utils/strptime.py,sha256=tnPJ_C4wKZAGwW03z5-XHy5ykZ3lP6RLpw6QR-jT-f0,2853
+dateparser/utils/strptime.py,sha256=YgdfLAwedcer3sdwtq0gol2TBpYIqANvFrf4u0K3mAg,3948
+dateparser/utils/time_spans.py,sha256=8DLVRU7iM_v5tJhuYdjhOaTH2MxroguXorxxaJUf3-E,5303
+dateparser-1.3.0.dist-info/licenses/AUTHORS.rst,sha256=xyYeT2AGKVrsHYxoOxgDE8XmSK7VNtJNqFzw25JLE2g,711
+dateparser-1.3.0.dist-info/licenses/LICENSE,sha256=t122Vbt6QqjoVh0NuHMVi7naudRoryRAAPAtfdg-l_Q,1468
 dateparser_cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dateparser_cli/cli.py,sha256=pZSVwZO_N1AfPJfbbTHgvEnV8kmvyKmd6YQLYT3epis,991
 dateparser_cli/exceptions.py,sha256=ifwai5On6opuhUpBHMoz0iFkybtZg7m3gHHnxtOEoEk,58
 dateparser_cli/fasttext_manager.py,sha256=Q1I42NFR6YghTRySjNA9WFQnJ6l_2KDW4VaxXU1amiA,1495
 dateparser_cli/utils.py,sha256=XERf49Ed3Avx91sjC6Rz1Lii9yvt59LXKhOsZ3SuN9E,645
 dateparser_data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-dateparser_data/settings.py,sha256=AOjSJ8oZqCw8WxHMLUS3bT6njU1citYSICjqBtZu38s,849
+dateparser_data/settings.py,sha256=7rSLmqtbw8DKGvhs23D4aqP-IZbhI-dGaI2n8l_7vuk,977
 dateparser_scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dateparser_scripts/get_cldr_data.py,sha256=A6ziFXtK72UvGDgHYavDqadsnBH5ezM1RgpXydk-DPA,16926
 dateparser_scripts/order_languages.py,sha256=BkYmAqFvoMvj3I7xcjeutz0Bx5VQQky68Y5fNrNzLmg,7201
 dateparser_scripts/update_supported_languages_and_locales.py,sha256=BaHzzCiLKvkhKcal44CyedZNIUrBrI4fm0LxHicRJ8g,1460
 dateparser_scripts/utils.py,sha256=Uw4HbgwbKYuUeztUw9OQqtzPtjmBxBBqGytLXjtSia8,2579
-dateparser_scripts/write_complete_data.py,sha256=w1pExoB7Z5oN02pSMvkzN2K-kQ_5UbehAdvTZ_bYUCQ,4540
-dateparser-1.2.1.dist-info/AUTHORS.rst,sha256=xyYeT2AGKVrsHYxoOxgDE8XmSK7VNtJNqFzw25JLE2g,711
-dateparser-1.2.1.dist-info/LICENSE,sha256=t122Vbt6QqjoVh0NuHMVi7naudRoryRAAPAtfdg-l_Q,1468
-dateparser-1.2.1.dist-info/METADATA,sha256=xBE9ekzZoqtRzII8t2YytRzToJ0qJ3suxF0qjBJPyEQ,29406
-dateparser-1.2.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-dateparser-1.2.1.dist-info/entry_points.txt,sha256=QPwc8kOjbaaxJdyQXiix9sGbUjC_G_Ga5LgJ_11KKAs,68
-dateparser-1.2.1.dist-info/top_level.txt,sha256=LujVBIKC69tvws1XkgyOFRDjEEd-E1SjAirYrhEbqn8,61
-dateparser-1.2.1.dist-info/RECORD,,
+dateparser_scripts/write_complete_data.py,sha256=RS_0k-TZAdiCG7P7aRiZDgPhfFwlzFIk3df6a0846cw,4543
+dateparser-1.3.0.dist-info/METADATA,sha256=7KawAlvH8rbrbloiIYfJfr8PQ2lEvwUoDjPnaMgrqhk,30933
+dateparser-1.3.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+dateparser-1.3.0.dist-info/entry_points.txt,sha256=QPwc8kOjbaaxJdyQXiix9sGbUjC_G_Ga5LgJ_11KKAs,68
+dateparser-1.3.0.dist-info/top_level.txt,sha256=LujVBIKC69tvws1XkgyOFRDjEEd-E1SjAirYrhEbqn8,61
+dateparser-1.3.0.dist-info/RECORD,,

{dateparser-1.2.1.dist-info → dateparser-1.3.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

dateparser_data/settings.py

@@ -26,6 +26,10 @@ settings = {
     "DEFAULT_LANGUAGES": [],
     # Optional language detection
     "LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD": 0.5,
+    # Time span settings
+    "RETURN_TIME_SPAN": False,
+    "DEFAULT_START_OF_WEEK": "monday",
+    "DEFAULT_DAYS_IN_MONTH": 30,
     # Other settings
     "RETURN_TIME_AS_PERIOD": False,
     "PARSERS": default_parsers,

dateparser_scripts/write_complete_data.py

@@ -4,7 +4,7 @@ import shutil
 from collections import OrderedDict
 
 import regex as re
-from ruamel.yaml import RoundTripLoader
+from ruamel.yaml import YAML
 
 from dateparser_scripts.order_languages import avoid_languages
 from dateparser_scripts.utils import combine_dicts
@@ -55,7 +55,8 @@ def _get_complete_date_translation_data(language):
             cldr_data = json.load(f, object_pairs_hook=OrderedDict)
     if language in supplementary_languages:
         with open(supplementary_date_directory + language + ".yaml") as g:
-            supplementary_data = OrderedDict(RoundTripLoader(g).get_data())
+            yaml = YAML()
+            supplementary_data = OrderedDict(yaml.load(g))
     complete_data = combine_dicts(cldr_data, supplementary_data)
     if "name" not in complete_data:
         complete_data["name"] = language
@@ -88,7 +89,8 @@ def write_complete_data(in_memory=False):
         os.mkdir(date_translation_directory)
 
     with open(supplementary_directory + "base_data.yaml") as f:
-        base_data = RoundTripLoader(f).get_data()
+        yaml = YAML()
+        base_data = yaml.load(f)
 
     for language in all_languages:
         date_translation_data = _get_complete_date_translation_data(language)