From a0b0f1969dbb55d8f52774bfff5b526b26cfc10e Mon Sep 17 00:00:00 2001 From: jasongehring Date: Thu, 12 May 2022 15:25:38 +0200 Subject: [PATCH 1/2] Improvements to de --- dateparser/data/date_translation_data/de.py | 79 ++++++++++++++----- .../date_translation_data/de.yaml | 44 +++++++---- tests/test_languages.py | 5 ++ 3 files changed, 93 insertions(+), 35 deletions(-) diff --git a/dateparser/data/date_translation_data/de.py b/dateparser/data/date_translation_data/de.py index 6b3933c4c..da0594d02 100644 --- a/dateparser/data/date_translation_data/de.py +++ b/dateparser/data/date_translation_data/de.py @@ -37,7 +37,8 @@ ], "september": [ "sep", - "september" + "september", + "Sept" ], "october": [ "okt", @@ -53,38 +54,31 @@ ], "monday": [ "mo", - "montag", - "Mon" + "montag" ], "tuesday": [ "di", - "dienstag", - "Die" + "dienstag" ], "wednesday": [ "mi", - "mittwoch", - "Mit" + "mittwoch" ], "thursday": [ "do", - "donnerstag", - "Don" + "donnerstag" ], "friday": [ "fr", - "freitag", - "Fre" + "freitag" ], "saturday": [ "sa", - "samstag", - "Sam" + "samstag" ], "sunday": [ "so", - "sonntag", - "Son" + "sonntag" ], "am": [ "vorm" @@ -152,16 +146,23 @@ "dieses jahr" ], "1 day ago": [ - "gestern" + "gestern", + "am vortag" ], "1 month ago": [ - "letzten monat" + "letzten monat", + "vorherigen Monat", + "vor einem Monat" ], "1 week ago": [ - "letzte woche" + "letzte woche", + "vorherige Woche", + "vor einer woche" ], "1 year ago": [ - "letztes jahr" + "letztes jahr", + "vor einem Jahr", + "vorheriges Jahr" ], "in 1 day": [ "morgen" @@ -288,6 +289,7 @@ "uhr", "um", "und", + "am", " ", "'", ",", @@ -319,38 +321,77 @@ { "ein": "1" }, + { + "eins": "1" + }, + { + "ersten": "1" + }, { "zwei": "2" }, + { + "zweiten": "2" + }, { "drei": "3" }, + { + "dritten": "3" + }, { "vier": "4" }, + { + "vierten": "4" + }, { "fünf": "5" }, + { + "fünften": "5" + }, { "sechs": "6" }, + { + "sechsten": "6" + }, { "sieben": "7" }, + { + "siebten": "7" + }, { "acht": "8" }, + { + "achten": "8" + }, { "neun": "9" }, + { + "neunten": "9" + }, { "zehn": "10" }, + { + "zehnten": "10" + }, { "elf": "11" }, + { + "elften": "11" + }, { "zwölf": "12" + }, + { + "zwölften": "12" } ] } diff --git a/dateparser_data/supplementary_language_data/date_translation_data/de.yaml b/dateparser_data/supplementary_language_data/date_translation_data/de.yaml index bf9b8f185..b27f1727c 100644 --- a/dateparser_data/supplementary_language_data/date_translation_data/de.yaml +++ b/dateparser_data/supplementary_language_data/date_translation_data/de.yaml @@ -1,28 +1,15 @@ -skip: ["etwa", "uhr", "um", "und"] +skip: ["etwa", "uhr", "um", "und", "am"] sentence_splitter_group : 1 -monday: - - Mon -tuesday: - - Die -wednesday: - - Mit -thursday: - - Don -friday: - - Fre -saturday: - - Sam -sunday: - - Son - january: - Jänner february: - Feber march: - Mrz +september: + - Sept year: - Jahre @@ -49,10 +36,21 @@ in: - im relative-type: + 1 day ago: + - am vortag 2 day ago: - vorgestern in 2 day: - übermorgen + 1 month ago: + - vorherigen Monat + - vor einem Monat + 1 week ago: + - vorherige Woche + - vor einer woche + 1 year ago: + - vor einem Jahr + - vorheriges Jahr relative-type-regex: \1 hour ago: @@ -66,14 +64,28 @@ simplifications: - einer: '1' - einem: '1' - ein: '1' + - eins: '1' + - ersten: '1' - zwei: '2' + - zweiten: '2' - drei: '3' + - dritten: '3' - vier: '4' + - vierten: '4' - fünf: '5' + - fünften : '5' - sechs: '6' + - sechsten: '6' - sieben: '7' + - siebten: '7' - acht: '8' + - achten: '8' - neun: '9' + - neunten: '9' - zehn: '10' + - zehnten: '10' - elf: '11' + - elften: '11' - zwölf: '12' + - zwölften: '12' + diff --git a/tests/test_languages.py b/tests/test_languages.py index a9d292d8f..e6c2c7bc9 100644 --- a/tests/test_languages.py +++ b/tests/test_languages.py @@ -829,6 +829,11 @@ def test_translation(self, shortname, datetime_string, expected_translation): param('de', "vor 3 Stunden", "3 hour ago"), param('de', "vor 2 Monaten", "2 month ago"), param('de', "vor 2 Monaten, 2 Wochen", "2 month ago 2 week"), + param('de', "4 Sept. 2022", "4 september 2022"), + param('de', "am Vortag", "1 day ago"), + param('de', "vorherigen Monat", "1 month ago"), + param('de', "vor einem Monat", "1 month ago"), + param('de', "am Ersten Dezember 2022", "1 december 2022"), # French param('fr', "avant-hier", "2 day ago"), param('fr', "hier", "1 day ago"), From c5ad48f362834eec6d5d72cb4660a90ceb810dbc Mon Sep 17 00:00:00 2001 From: jasongehring Date: Thu, 12 May 2022 20:59:18 +0200 Subject: [PATCH 2/2] Improvements to the tests --- tests/test_languages.py | 4 ++-- tests/test_search.py | 3 +-- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/tests/test_languages.py b/tests/test_languages.py index e6c2c7bc9..578257645 100644 --- a/tests/test_languages.py +++ b/tests/test_languages.py @@ -829,11 +829,11 @@ def test_translation(self, shortname, datetime_string, expected_translation): param('de', "vor 3 Stunden", "3 hour ago"), param('de', "vor 2 Monaten", "2 month ago"), param('de', "vor 2 Monaten, 2 Wochen", "2 month ago 2 week"), - param('de', "4 Sept. 2022", "4 september 2022"), + param('de', "4 Sept 2022", "4 september 2022"), param('de', "am Vortag", "1 day ago"), param('de', "vorherigen Monat", "1 month ago"), param('de', "vor einem Monat", "1 month ago"), - param('de', "am Ersten Dezember 2022", "1 december 2022"), + param('de', "Ersten Dezember 2022", "1 december 2022"), # French param('fr', "avant-hier", "2 day ago"), param('fr', "hier", "1 day ago"), diff --git a/tests/test_search.py b/tests/test_search.py index 1ea7b7bff..0fbaa89ee 100644 --- a/tests/test_search.py +++ b/tests/test_search.py @@ -347,8 +347,7 @@ def test_search_date_string(self, shortname, datetime_string): # German param('de', 'Die UdSSR blieb gemäß dem Neutralitätspakt ' 'vom 13. April 1941 gegenüber Japan vorerst neutral.', - [('Die', datetime.datetime(1999, 12, 28, 0, 0)), - ('13. April 1941', datetime.datetime(1941, 4, 13, 0, 0))], + [('13. April 1941', datetime.datetime(1941, 4, 13, 0, 0))], settings={'RELATIVE_BASE': datetime.datetime(2000, 1, 1)}), # Indonesian