better date parsing
This commit is contained in:
@@ -0,0 +1,582 @@
|
||||
cases:
|
||||
- name: date_format_1
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "lorem ipsum 130218 lorem ipsum"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: date_format_2
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "lorem ipsum 2018 lorem ipsum"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: date_format_3
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "lorem ipsum 20180213 lorem ipsum"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: date_format_4
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "lorem ipsum 13.02.2018 lorem ipsum"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2018-02-13
|
||||
|
||||
- name: date_format_5
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "lorem ipsum 130218, 2018, 20180213 and lorem 13.02.2018 lorem ipsum"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2018-02-13
|
||||
|
||||
- name: date_format_6
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: |
|
||||
lorem ipsum
|
||||
Wohnort
|
||||
3100
|
||||
IBAN
|
||||
AT87 4534
|
||||
1234
|
||||
1234 5678
|
||||
BIC
|
||||
lorem ipsum
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: date_format_7
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: |
|
||||
lorem ipsum
|
||||
März 2019
|
||||
lorem ipsum
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- de
|
||||
expected:
|
||||
mode: single
|
||||
value: 2019-03-01
|
||||
|
||||
- name: date_format_8
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: |
|
||||
lorem ipsum
|
||||
Wohnort
|
||||
3100
|
||||
IBAN
|
||||
AT87 4534
|
||||
1234
|
||||
1234 5678
|
||||
BIC
|
||||
lorem ipsum
|
||||
März 2020
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- de
|
||||
expected:
|
||||
mode: single
|
||||
value: 2020-03-01
|
||||
|
||||
- name: date_format_9
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: |
|
||||
lorem ipsum
|
||||
27. Nullmonth 2020
|
||||
März 2020
|
||||
lorem ipsum
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- de
|
||||
expected:
|
||||
mode: single
|
||||
value: 2020-03-01
|
||||
|
||||
- name: date_format_10
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22-MAR-2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-22
|
||||
|
||||
- name: date_format_11
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22 MAR 2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-22
|
||||
|
||||
- name: date_format_12
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22/MAR/2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-22
|
||||
|
||||
- name: date_format_13
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22.MAR.2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-22
|
||||
|
||||
- name: date_format_14
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22.MAR 2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-22
|
||||
|
||||
- name: date_format_15
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22.MAR.22 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: date_format_16
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22.MAR,22 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: date_format_17
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22,MAR,2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: date_format_18
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22 MAR,2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: date_format_19
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 21st MAR 2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-21
|
||||
|
||||
- name: date_format_20
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 22nd March 2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-22
|
||||
|
||||
- name: date_format_21
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 2nd MAR 2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-02
|
||||
|
||||
- name: date_format_22
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 23rd MAR 2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-23
|
||||
|
||||
- name: date_format_23
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 24th MAR 2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-24
|
||||
|
||||
- name: date_format_24
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 21-MAR-2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-21
|
||||
|
||||
- name: date_format_25
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "Customer Number Currency 25TH MAR 2022 Credit Card 1934829304"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-25
|
||||
|
||||
- name: date_format_26
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "CHASE 0 September 25, 2019 JPMorgan Chase Bank, NA. P0 Box 182051"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: single
|
||||
value: 2019-09-25
|
||||
|
||||
- name: numeric_mdy_slash
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "03/17/2008"
|
||||
settings:
|
||||
DATE_ORDER: MDY
|
||||
expected:
|
||||
mode: single
|
||||
value: 2008-03-17
|
||||
|
||||
- name: crazy_date_past
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "01-07-0590 00:00:00"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: crazy_date_future
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "01-07-2350 00:00:00"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: crazy_date_with_spaces
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "20 408000l 2475"
|
||||
settings: {}
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: utf_month_names_decembre
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "13 décembre 2023"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2023-12-13
|
||||
|
||||
- name: utf_month_names_aout
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "13 août 2022"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-08-13
|
||||
|
||||
- name: utf_month_names_marz
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "11 März 2020"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2020-03-11
|
||||
|
||||
- name: utf_month_names_ozujka
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "17. ožujka 2018."
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2018-03-17
|
||||
|
||||
- name: utf_month_names_veljace
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "1. veljače 2016."
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2016-02-01
|
||||
|
||||
- name: utf_month_names_unora
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "15. února 1985"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 1985-02-15
|
||||
|
||||
- name: utf_month_names_zari
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "30. září 2011"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2011-09-30
|
||||
|
||||
- name: utf_month_names_kvetna
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "28. května 1990"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 1990-05-28
|
||||
|
||||
- name: utf_month_names_grudzien
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "1. grudzień 1997"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 1997-12-01
|
||||
|
||||
- name: utf_month_names_subat
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "17 Şubat 2024"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2024-02-17
|
||||
|
||||
- name: utf_month_names_agustos
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "30 Ağustos 2012"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2012-08-30
|
||||
|
||||
- name: utf_month_names_eylul
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "17 Eylül 2000"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
expected:
|
||||
mode: single
|
||||
value: 2000-09-17
|
||||
|
||||
- name: utf_month_names_oktober
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "5. október 1992"
|
||||
settings:
|
||||
DATE_PARSER_LANGUAGES:
|
||||
- fr
|
||||
- de
|
||||
- hr
|
||||
- cs
|
||||
- pl
|
||||
- tr
|
||||
- hu
|
||||
expected:
|
||||
mode: single
|
||||
value: 1992-10-05
|
||||
|
||||
- name: multiple_dates
|
||||
parser: parse_date_generator
|
||||
filename: null
|
||||
content: |
|
||||
This text has multiple dates.
|
||||
For example 02.02.2018, 22 July 2022 and December 2021.
|
||||
But not 24-12-9999 because it's in the future...
|
||||
settings: {}
|
||||
expected:
|
||||
mode: multiple
|
||||
value:
|
||||
- 2018-02-02
|
||||
- 2022-07-22
|
||||
- 2021-12-01
|
||||
|
||||
- name: filename_date_parse_valid_ymd
|
||||
parser: parse_date
|
||||
filename: /tmp/Scan-2022-04-01.pdf
|
||||
content: "No date in here"
|
||||
settings:
|
||||
FILENAME_DATE_ORDER: YMD
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-04-01
|
||||
|
||||
- name: filename_date_parse_valid_dmy
|
||||
parser: parse_date
|
||||
filename: /tmp/Scan-10.01.2021.pdf
|
||||
content: "No date in here"
|
||||
settings:
|
||||
FILENAME_DATE_ORDER: DMY
|
||||
expected:
|
||||
mode: single
|
||||
value: 2021-01-10
|
||||
|
||||
- name: filename_date_parse_invalid
|
||||
parser: parse_date
|
||||
filename: "/tmp/20 408000l 2475 - test.pdf"
|
||||
content: "No date in here"
|
||||
settings:
|
||||
FILENAME_DATE_ORDER: YMD
|
||||
expected:
|
||||
mode: none
|
||||
|
||||
- name: filename_date_ignored_use_content
|
||||
parser: parse_date
|
||||
filename: /tmp/Scan-2022-04-01.pdf
|
||||
content: "The matching date is 24.03.2022"
|
||||
settings:
|
||||
FILENAME_DATE_ORDER: YMD
|
||||
IGNORE_DATES:
|
||||
- 2022-04-01
|
||||
expected:
|
||||
mode: single
|
||||
value: 2022-03-24
|
||||
|
||||
- name: ignored_dates_default_order
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "lorem ipsum 110319, 20200117 and lorem 13.02.2018 lorem ipsum"
|
||||
settings:
|
||||
IGNORE_DATES:
|
||||
- 2019-11-03
|
||||
- 2020-01-17
|
||||
expected:
|
||||
mode: single
|
||||
value: 2018-02-13
|
||||
|
||||
- name: ignored_dates_order_ymd
|
||||
parser: parse_date
|
||||
filename: null
|
||||
content: "lorem ipsum 190311, 20200117 and lorem 13.02.2018 lorem ipsum"
|
||||
settings:
|
||||
FILENAME_DATE_ORDER: YMD
|
||||
IGNORE_DATES:
|
||||
- 2019-11-03
|
||||
- 2020-01-17
|
||||
expected:
|
||||
mode: single
|
||||
value: 2018-02-13
|
||||
Reference in New Issue
Block a user