File search between two dates with ansible

Question

I'm looking for a way to do a file search between two dates and I'm searching for a method to make this more beautiful than my example below , I specify that this example code below works

I know the ansible find module exists but I can't perform a search between two dates like I want to implement in my example (or at least I didn't succeed)

file search between the 2022-09-26 and the 2022-10-26
create some files for the test touch -d "35 days ago" /tmp/toto /tmp/tata /tmp/tutu.zip
run the playbook

- name: "test find"
  gather_facts: false
  become: yes
  hosts: "localhost"
  tasks:
  - name: "create vars"
    set_fact:
      path_to_find:             "/tmp"
      BEGIN_DATE:               "{{lookup('pipe','date -d \"2 months ago\" -I')}}"
      END_DATE:                 "{{lookup('pipe','date -d \"1 months ago\" -I')}}"
      ZIP_NAME:                 "archive_test_name.zip"

  - name: "find between two dates "
    shell: find "{{ path_to_find }}" -type f ! -name "*.zip" -newermt "{{ BEGIN_DATE }}" ! -newermt "{{ END_DATE }}"
    register: FindFiles

  - debug:
      msg: "{{ FindFiles }}"

I hope someone has an idea or a best practice !

Vladimir Botka · Accepted Answer

Given the files for testing

shell> ls -ogla /tmp/test/
total 28
drwxrwxr-x  2  4096 Nov 25 21:23 .
drwxrwxrwt 70 20480 Nov 25 22:28 ..
-rw-rw-r--  1     0 Jul 25 00:00 file1
-rw-rw-r--  1     0 Aug 25 00:00 file2
-rw-rw-r--  1     0 Sep 25 00:00 file3
-rw-rw-r--  1     0 Oct 25 00:00 file4
-rw-rw-r--  1     0 Nov 25 00:00 file5

Find lists of files older than the dates and create the difference between these lists.

In addition to the declarations

  begin_date: "{{ lookup('pipe', 'date -d \"2 months ago\" -I') }}"
  end_date: "{{ lookup('pipe', 'date -d \"1 months ago\" -I') }}"

Declare the variables

  today: "{{ '%Y-%m-%d'|strftime }}"
  begin_days: "{{ ((today|to_datetime('%Y-%m-%d')) -
                   (begin_date|to_datetime('%Y-%m-%d'))).days }}"
  end_days: "{{ ((today|to_datetime('%Y-%m-%d')) -
                 (end_date|to_datetime('%Y-%m-%d'))).days }}"

gives the date of today and the number of days from begin_date and end_date

  begin_date: 2022-09-25
  end_date: 2022-10-25
  today: 2022-11-25
  begin_days: 61
  end_days: 31

Find and register files where the modification time is older than begin_date and end_date

    - find:
        path: /tmp/test
        age: "{{ begin_days }}d"
      register: begin

    - find:
        path: /tmp/test
        age: "{{ end_days }}d"
      register: end

Declare the variables

  begin_files: "{{ begin.files|map(attribute='path')|list }}"
  end_files: "{{ end.files|map(attribute='path')|list }}"
  my_files: "{{ end_files|difference(begin_files) }}"

gives the lists of files where the modification time is older than begin_date and end_date. The difference between these lists my_files is what you're looking for

  begin_files: ['/tmp/test/file3', '/tmp/test/file2', '/tmp/test/file1']
  end_files: ['/tmp/test/file3', '/tmp/test/file4', '/tmp/test/file2', '/tmp/test/file1']
  my_files: ['/tmp/test/file4']

^{Example of a complete playbook for testing
- hosts: localhost

vars:

today: "{{ '%Y-%m-%d'|strftime }}"
begin_date: "{{ lookup('pipe', 'date -d \"2 months ago\" -I') }}"
end_date: "{{ lookup('pipe', 'date -d \"1 months ago\" -I') }}"
begin_days: "{{ ((today|to_datetime('%Y-%m-%d')) -
(begin_date|to_datetime('%Y-%m-%d'))).days }}"
end_days: "{{ ((today|to_datetime('%Y-%m-%d')) -
(end_date|to_datetime('%Y-%m-%d'))).days }}"
begin_files: "{{ begin.files|map(attribute='path')|list }}"
end_files: "{{ end.files|map(attribute='path')|list }}"
my_files: "{{ end_files|difference(begin_files) }}"

tasks:

- debug:
msg: |
today: {{ today }}
begin_date: {{ begin_date }}
end_date: {{ end_date }}
begin_days: {{ begin_days }}
end_days: {{ end_days }}

- find:
path: /tmp/test
age: "{{ begin_days }}d"
register: begin

- find:
path: /tmp/test
age: "{{ end_days }}d"
register: end

- debug:
msg: |
begin_files: {{ begin_files }}
end_files: {{ end_files }}
my_files: {{ my_files }}}

Collect the status of the files and select files by time.

Change the format of the dates to seconds

  begin_date_cmd: "date -d '2 months ago' '+%s'"
  begin_date: "{{ lookup('pipe', begin_date_cmd) }}"
  end_date_cmd: "date -d '1 months ago' '+%s'"
  end_date: "{{ lookup('pipe', end_date_cmd) }}"

gives

  begin_date: 1664143922
  end_date: 1666735922

Declare the variable

  files_all: "{{ all.files|map(attribute='path')|list }}"

and get the list of all files

    - find:
        path: /tmp/test
      register: all

Collect the status of all files

    - stat:
        path: "{{ item }}"
      register: st
      loop: "{{ files_all }}"

Declare the list where the modification time is bigger than begin_date and less than end_date

  my_files: "{{ st.results|selectattr('stat.mtime', 'gt', begin_date|float)|
                           selectattr('stat.mtime', 'lt', end_date|float)|
                           map(attribute='item')|list }}"

gives

  my_files:
  - /tmp/test/file4

^{Example of a complete playbook for testing
- hosts: localhost

vars:

begin_date_cmd: "date -d '2 months ago' '+%s'"
begin_date: "{{ lookup('pipe', begin_date_cmd) }}"
end_date_cmd: "date -d '1 months ago' '+%s'"
end_date: "{{ lookup('pipe', end_date_cmd) }}"
files_all: "{{ all.files|map(attribute='path')|list }}"
my_files: "{{ st.results|selectattr('stat.mtime', 'gt', begin_date|float)|
selectattr('stat.mtime', 'lt', end_date|float)|
map(attribute='item')|list }}"

tasks:

- debug:
msg: |
begin_date: {{ begin_date }}
end_date: {{ end_date }}

- find:
path: /tmp/test
register: all
- debug:
var: files_all

- stat:
path: "{{ item }}"
register: st
loop: "{{ files_all }}"
- debug:
var: st

- debug:
var: my_files}

File search between two dates with ansible

Answers (2)

Related Questions