.github/FUNDING.yml

@@ -0,0 +1 @@
+github: akoumjian

.github/workflows/python-package.yml

@@ -0,0 +1,40 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Python package
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.8", "3.9", "3.10"]
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8 pytest
+        python setup.py install
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        pytest

.github/workflows/python-publish.yml

@@ -0,0 +1,39 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build --wheel
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

MANIFEST.in

@@ -0,0 +1 @@
+include LICENSE

README.rst

@@ -1,9 +1,9 @@
 datefinder - extract dates from text
 ====================================
 
-.. image:: https://img.shields.io/travis/akoumjian/datefinder/master.svg
-    :target: https://travis-ci.org/akoumjian/datefinder
-    :alt: travis build status
+.. image:: https://github.com/akoumjian/datefinder/actions/workflows/python-package.yml/badge.svg
+    :target: https://github.com/akoumjian/datefinder
+    :alt: Build Status
 
 .. image:: https://img.shields.io/pypi/dm/datefinder.svg
     :target: https://pypi.python.org/pypi/datefinder/
@@ -13,10 +13,6 @@ datefinder - extract dates from text
     :target: https://pypi.python.org/pypi/datefinder
     :alt: pypi version
 
-.. image:: https://img.shields.io/gitter/room/nwjs/nw.js.svg
-    :target: https://gitter.im/datefinder/Lobby
-    :alt: gitter chat
-
 
 A python module for locating dates inside text. Use this package to extract all sorts 
 of date like strings from a document and turn them into datetime objects.
@@ -28,10 +24,13 @@ This module finds the likely datetime strings and then uses
 Installation
 ------------
 
+**With pip**
+
 .. code-block:: sh
 
     pip install datefinder
 
+**Note:  I do not publish the version on conda forge and cannot verify its integrity.**
 
 How to Use
 ----------
@@ -58,8 +57,10 @@ How to Use
     2005-01-15 00:00:00
 
 
-Support
--------
+Demo
+----
+
+-  🎞️ `Video demo`_ by Calmcode.io. :star: 
 
-You can talk to us on `Gitter <https://gitter.im/datefinder/Lobby>`_ or just submit an issue on `github <https://github.com/akoumjian/datefinder/issues/>`_. 
+.. _Video demo: https://calmcode.io/shorts/datefinder.py.html
 

datefinder/__init__.py

@@ -5,6 +5,7 @@
 from datefinder.date_fragment import DateFragment
 from .constants import (
     REPLACEMENTS,
+    DELIMITERS_PATTERN,
     TIMEZONE_REPLACEMENTS,
     STRIP_CHARS,
     DATE_REGEX,
@@ -20,8 +21,14 @@ class DateFinder(object):
     Locates dates in a text
     """
 
-    def __init__(self, base_date=None):
+    def __init__(self, base_date=None, first="month"):
         self.base_date = base_date
+        self.dayfirst = False
+        self.yearfirst = False
+        if first == "day":
+            self.dayfirst = True
+        if first == "year":
+            self.yearfirst = True
 
     def find_dates(self, text, source=False, index=False, strict=False):
 
@@ -64,8 +71,14 @@ def _find_and_replace(self, date_string, captures):
             # 2. match ' to'
             # 3. match ' to '
             # but never match r'(\s|)to(\s|)' which would make 'october' > 'ocber'
+            # but also include delimiters, like this 'date: '
+            full_match_pattern = (
+                r"(^|{delimiters_pattern}){key}($|{delimiters_pattern})".format(
+                    delimiters_pattern=DELIMITERS_PATTERN, key=key
+                )
+            )
             date_string = re.sub(
-                r"(^|\s)" + key + r"(\s|$)",
+                full_match_pattern,
                 replacement,
                 date_string,
                 flags=re.IGNORECASE,
@@ -99,7 +112,12 @@ def parse_date_string(self, date_string, captures):
         # For well formatted string, we can already let dateutils parse them
         # otherwise self._find_and_replace method might corrupt them
         try:
-            as_dt = parser.parse(date_string, default=self.base_date)
+            as_dt = parser.parse(
+                date_string,
+                default=self.base_date,
+                dayfirst=self.dayfirst,
+                yearfirst=self.yearfirst,
+            )
         except (ValueError, OverflowError):
             # replace tokens that are problematic for dateutil
             date_string, tz_string = self._find_and_replace(date_string, captures)
@@ -113,7 +131,12 @@ def parse_date_string(self, date_string, captures):
 
             try:
                 logger.debug("Parsing {0} with dateutil".format(date_string))
-                as_dt = parser.parse(date_string, default=self.base_date)
+                as_dt = parser.parse(
+                    date_string,
+                    default=self.base_date,
+                    dayfirst=self.dayfirst,
+                    yearfirst=self.yearfirst,
+                )
             except Exception as e:
                 logger.debug(e)
                 as_dt = None
@@ -139,9 +162,11 @@ def extract_date_strings_inner(self, text, text_start=0, strict=False):
         if rng and len(rng) > 1:
             range_strings = []
             for range_str in rng:
-                range_strings.extend(self.extract_date_strings_inner(range_str[0],
-                                                                     text_start=range_str[1][0],
-                                                                     strict=strict))
+                range_strings.extend(
+                    self.extract_date_strings_inner(
+                        range_str[0], text_start=range_str[1][0], strict=strict
+                    )
+                )
             for range_string in range_strings:
                 yield range_string
             return
@@ -159,6 +184,7 @@ def extract_date_strings_inner(self, text, text_start=0, strict=False):
             # digits_modifiers = captures.get('digits_modifiers')
             # days = captures.get('days')
             months = captures.get("months")
+            years = captures.get("years")
             # timezones = captures.get('timezones')
             # delimiters = captures.get('delimiters')
             # time_periods = captures.get('time_periods')
@@ -169,9 +195,16 @@ def extract_date_strings_inner(self, text, text_start=0, strict=False):
                 if len(digits) == 3:  # 12-05-2015
                     complete = True
                 elif (len(months) == 1) and (
-                        len(digits) == 2
+                    len(digits) == 2
                 ):  # 19 February 2013 year 09:10
                     complete = True
+                elif (len(years) == 1) and (len(digits) == 2):  # 09/06/2018
+                    complete = True
+
+                elif (
+                    (len(years) == 1) and (len(months) == 1) and (len(digits) == 1)
+                ):  # '19th day of May, 2015'
+                    complete = True
 
                 if not complete:
                     continue
@@ -185,12 +218,12 @@ def extract_date_strings_inner(self, text, text_start=0, strict=False):
             yield match_str, indices, captures
 
     def tokenize_string(self, text):
-        '''
+        """
         Get matches from source text. Method merge_tokens will later compose
         potential date strings out of these matches.
         :param text: source text like 'the big fight at 2p.m. mountain standard time on ufc.com'
         :return: [(match_text, match_group, {match.capturesdict()}), ...]
-        '''
+        """
         items = []
 
         last_index = 0
@@ -202,19 +235,19 @@ def tokenize_string(self, text):
             group = self.get_token_group(captures)
 
             if indices[0] > last_index:
-                items.append((text[last_index:indices[0]], '', {}))
+                items.append((text[last_index : indices[0]], "", {}))
             items.append((match_str, group, captures))
             last_index = indices[1]
         if last_index < len(text):
-            items.append((text[last_index:len(text)], '', {}))
+            items.append((text[last_index : len(text)], "", {}))
         return items
 
     def merge_tokens(self, tokens):
-        '''
+        """
         Makes potential date strings out of matches, got from tokenize_string method.
         :param tokens: [(match_text, match_group, {match.capturesdict()}), ...]
         :return: potential date strings
-        '''
+        """
         MIN_MATCHES = 3
         fragments = []
         frag = DateFragment()
@@ -264,7 +297,7 @@ def get_token_group(captures):
             lst = captures.get(gr)
             if lst and len(lst) > 0:
                 return gr
-        return ''
+        return ""
 
     @staticmethod
     def split_date_range(text):
@@ -284,7 +317,9 @@ def split_date_range(text):
         return parts
 
 
-def find_dates(text, source=False, index=False, strict=False, base_date=None):
+def find_dates(
+    text, source=False, index=False, strict=False, base_date=None, first="month"
+):
     """
     Extract datetime strings from text
 
@@ -306,9 +341,15 @@ def find_dates(text, source=False, index=False, strict=False, base_date=None):
     :param base_date:
         Set a default base datetime when parsing incomplete dates
     :type base_date: datetime
+    :param first:
+        Whether to interpret the the first value in an ambiguous 3-integer date
+        (01/02/03) as the month, day, or year. Values can be `month`, `day`, `year`.
+        Default is `month`.
+    :type first: str|unicode
+
 
     :return: Returns a generator that produces :mod:`datetime.datetime` objects,
         or a tuple with the source text and index, if requested
     """
-    date_finder = DateFinder(base_date=base_date)
+    date_finder = DateFinder(base_date=base_date, first=first)
     return date_finder.find_dates(text, source=source, index=index, strict=strict)

datefinder/constants.py

@@ -4,13 +4,12 @@
 POSITIONNAL_TOKENS = r"next|last"
 DIGITS_PATTERN = r"\d+"
 DIGITS_SUFFIXES = r"st|th|rd|nd"
-DAYS_PATTERN = "monday|tuesday|wednesday|thursday|friday|saturday|sunday|mon|tue|tues|wed|thur|thurs|fri|sat|sun"
-MONTHS_PATTERN = r"january|february|march|april|may|june|july|august|september|october|november|december|enero|febrero|marzo|abril|mayo|junio|julio|agosto|septiembre|octubre|noviembre|diciembre|jan\.?|ene\.?|feb\.?|mar\.?|apr\.?|abr\.?|may\.?|jun\.?|jul\.?|aug\.?|ago\.?|sep\.?|sept\.?|oct\.?|nov\.?|dec\.?|dic\.?"
+DAYS_PATTERN = "monday|tuesday|wednesday|thursday|friday|saturday|sunday|mandag|tirsdag|onsdag|torsdag|fredag|lørdag|søndag|mon|tue|tues|wed|thu|thur|thurs|fri|sat|sun|man|tir|tirs|ons|tor|tors|fre|lør|søn"
+MONTHS_PATTERN = r"january|february|march|april|may|june|july|august|september|october|november|december|enero|febrero|marzo|abril|mayo|junio|julio|agosto|septiembre|octubre|noviembre|diciembre|januar|februar|marts|april|maj|juni|juli|august|september|oktober|november|december|jan[\.\s]|ene[\.\s]|feb[\.\s]|mar[\.\s]|apr[\.\s]|abr[\.\s]|may[\.\s]|maj[\.\s]|jun[\.\s]|jul[\.\s]|aug[\.\s]|ago[\.\s]|sep[^A-Za-z]|sept[\.\s]|oct[\.\s]|okt[\.\s]|nov[\.\s]|dec[\.\s]|dic[\.\s]"
 TIMEZONES_PATTERN = "ACDT|ACST|ACT|ACWDT|ACWST|ADDT|ADMT|ADT|AEDT|AEST|AFT|AHDT|AHST|AKDT|AKST|AKTST|AKTT|ALMST|ALMT|AMST|AMT|ANAST|ANAT|ANT|APT|AQTST|AQTT|ARST|ART|ASHST|ASHT|AST|AWDT|AWST|AWT|AZOMT|AZOST|AZOT|AZST|AZT|BAKST|BAKT|BDST|BDT|BEAT|BEAUT|BIOT|BMT|BNT|BORT|BOST|BOT|BRST|BRT|BST|BTT|BURT|CANT|CAPT|CAST|CAT|CAWT|CCT|CDDT|CDT|CEDT|CEMT|CEST|CET|CGST|CGT|CHADT|CHAST|CHDT|CHOST|CHOT|CIST|CKHST|CKT|CLST|CLT|CMT|COST|COT|CPT|CST|CUT|CVST|CVT|CWT|CXT|ChST|DACT|DAVT|DDUT|DFT|DMT|DUSST|DUST|EASST|EAST|EAT|ECT|EDDT|EDT|EEDT|EEST|EET|EGST|EGT|EHDT|EMT|EPT|EST|ET|EWT|FET|FFMT|FJST|FJT|FKST|FKT|FMT|FNST|FNT|FORT|FRUST|FRUT|GALT|GAMT|GBGT|GEST|GET|GFT|GHST|GILT|GIT|GMT|GST|GYT|HAA|HAC|HADT|HAE|HAP|HAR|HAST|HAT|HAY|HDT|HKST|HKT|HLV|HMT|HNA|HNC|HNE|HNP|HNR|HNT|HNY|HOVST|HOVT|HST|ICT|IDDT|IDT|IHST|IMT|IOT|IRDT|IRKST|IRKT|IRST|ISST|IST|JAVT|JCST|JDT|JMT|JST|JWST|KART|KDT|KGST|KGT|KIZST|KIZT|KMT|KOST|KRAST|KRAT|KST|KUYST|KUYT|KWAT|LHDT|LHST|LINT|LKT|LMT|LMT|LMT|LMT|LRT|LST|MADMT|MADST|MADT|MAGST|MAGT|MALST|MALT|MART|MAWT|MDDT|MDST|MDT|MEST|MET|MHT|MIST|MIT|MMT|MOST|MOT|MPT|MSD|MSK|MSM|MST|MUST|MUT|MVT|MWT|MYT|NCST|NCT|NDDT|NDT|NEGT|NEST|NET|NFT|NMT|NOVST|NOVT|NPT|NRT|NST|NT|NUT|NWT|NZDT|NZMT|NZST|OMSST|OMST|ORAST|ORAT|PDDT|PDT|PEST|PET|PETST|PETT|PGT|PHOT|PHST|PHT|PKST|PKT|PLMT|PMDT|PMMT|PMST|PMT|PNT|PONT|PPMT|PPT|PST|PT|PWT|PYST|PYT|QMT|QYZST|QYZT|RET|RMT|ROTT|SAKST|SAKT|SAMT|SAST|SBT|SCT|SDMT|SDT|SET|SGT|SHEST|SHET|SJMT|SLT|SMT|SRET|SRT|SST|STAT|SVEST|SVET|SWAT|SYOT|TAHT|TASST|TAST|TBIST|TBIT|TBMT|TFT|THA|TJT|TKT|TLT|TMT|TOST|TOT|TRST|TRT|TSAT|TVT|ULAST|ULAT|URAST|URAT|UTC|UYHST|UYST|UYT|UZST|UZT|VET|VLAST|VLAT|VOLST|VOLT|VOST|VUST|VUT|WARST|WART|WAST|WAT|WDT|WEDT|WEMT|WEST|WET|WFT|WGST|WGT|WIB|WIT|WITA|WMT|WSDT|WSST|WST|WT|XJT|YAKST|YAKT|YAPT|YDDT|YDT|YEKST|YEKST|YEKT|YEKT|YERST|YERT|YPT|YST|YWT|zzz"
 ## explicit north american timezones that get replaced
 NA_TIMEZONES_PATTERN = "pacific|eastern|mountain|central"
 ALL_TIMEZONES_PATTERN = TIMEZONES_PATTERN + "|" + NA_TIMEZONES_PATTERN
-DELIMITERS_PATTERN = r"[/\:\-\,\s\_\+\@]+"
 
 # Allows for straightforward datestamps e.g 2017, 201712, 20171223. Created with:
 #  YYYYMM_PATTERN = '|'.join(['19\d\d'+'{:0>2}'.format(mon)+'|20\d\d'+'{:0>2}'.format(mon) for mon in range(1, 13)])
@@ -163,7 +162,7 @@
 STRIP_CHARS = " \n\t:-.,_"
 
 # split ranges
-RANGE_SPLIT_PATTERN = r'\Wto\W|\Wthrough\W'
+RANGE_SPLIT_PATTERN = r'\Wto\W|\Wthrough\W|\W-\W'
 
 RANGE_SPLIT_REGEX =  re.compile(RANGE_SPLIT_PATTERN,
     re.IGNORECASE | re.MULTILINE | re.UNICODE | re.DOTALL)

setup.py

@@ -23,7 +23,7 @@
     # Versions should comply with PEP440.  For a discussion on single-sourcing
     # the version across setup.py and the project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
-    version="0.7.1",
+    version="0.7.3",
     description="Extract datetime objects from strings",
     long_description=long_description,
     # The project's main homepage.