Merge branch 'develop' into 2411-metadata-parsed-datafiles-3

docs/Sprint-Review/sprint-81-summary.md

@@ -0,0 +1,55 @@
+
+# Sprint 81 Summary
+
+08/30/23 - 09/12/23
+
+Velocity: Dev (13)
+
+## Sprint Goal
+* Continue parsing engine development for TANF Sections (02 and 04) and close out subsmission history and metadata workflows (1613/12/10).
+* UX to continue regional staff and in-app messaging research, errors audit approach, and bridge onboarding to >90% of total users
+* DevOps to investigate singular ClamAV (2429), resolve utlity images for CircleCI and evaluate CI/CD pipeline.
+
+
+## Tickets
+### Completed/Merged
+* [#2626 improve parsing logging](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/2626)
+* [#1109 TANF (02) Parsing and Validation](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/1109)
+* [#2116 Container Registry Creation](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/2116)
+
+### Ready to Merge
+* N/A
+
+### Submitted (QASP Review, OCIO Review)
+* [#1613 As a developer, I need parsed file meta data (TANF Section 1)](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/board)
+
+### Closed (not merged)
+* N/A
+
+## Moved to Next Sprint (Blocked, Raft Review, In Progress, Current Sprint Backlog)
+### In Progress
+
+* [#2429 Singular ClamAV scanner](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/2429)
+* [#1111 TANF (04) Parsing and Validation](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/1111)
+* [#2664 (bug) file extension](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/2664)
+* [#2695 space-filled values update (TANF (01))](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/2695)
+* [#2411 As system admin, I awnt to view metadata on parsed datafiles](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/2411)
+* [#2536 [spike] Cat 4 validation](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/2536)
+
+
+### Blocked
+* N/A
+
+
+### Raft Review
+* [#1610 As a user, I need information about the acceptance of my data and a link for the error report](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/1610)
+* [#1612 Detailed case level metadata](https://app.zenhub.com/workspaces/sprint-board-5f18ab06dfd91c000f7e682e/issues/gh/raft-tech/tanf-app/1612)
+
+
+### Demo
+* Internal:
+    * 1109 - TANF Sec (02)
+    * 2626 - Parsing logging enhancements
+
+
+

docs/Technical-Documentation/CloudFoundry-DB-Connection.md

@@ -23,3 +23,36 @@ From [this github](https://github.com/cloud-gov/cf-service-connect) which has so
 
 > `cf connect-to-service tdp-backend-<name> tdp-db-dev`
 
+
+# How to DROP existing DB and Recreate a fresh DB
+
+### Connecting to DB service
+First step is to connect to the instance DB (see above).
+
+#### Optional: DB backup
+Before deleting the DB and recreating a fresh DB, you might want to create a backup from the existing data in case you decide to revert the DB changes back.
+
+For creating a DB backup, please see: `/tdpservice/scheduling/BACKUP_README.md`
+
+#### Drop and Recreate
+
+e.g: 
+>`cf connect-to-service tdp-backend-qasp tdp-db-dev`
+
+After connection to the DB is made (the step above will make a psql connection), then the following Postgres commands have to run:
+
+1. List the DBs: `\l`
+2. Potgres does not _DROP_ a database when you are connected to the same DB. As such, you will have to connect to a different DB using command:  
+>`\c {a_database}`
+   
+   A good candiadate is:
+>`\c postgres`
+3. find the associated DB name with instance. E.g: `tdp_db_dev_qasp`
+4. use the following command to delete the DB:
+>`DROP DATABASE {DB_NAME}`
+5. use the following command to create the DB:
+>`CREATE DATABASE {DB_NAME}`
+
+After the DB is created, since the database is cinoketely empty, we will need to redeploy the app again to create tables (or alternatively we can restore a good backup), and then we should run populate stt command to add STT data to the empty DB
+
+>`./manage.py populatestts`

tdrs-backend/tdpservice/parsers/parse.py

@@ -251,6 +251,50 @@ def manager_parse_line(line, schema_manager, generate_error, is_encrypted=False)
             )
         ])]
 
+
+def get_schema_manager_options(program_type):
+    """Return the allowed schema options."""
+    match program_type:
+        case 'TAN':
+            return {
+                'A': {
+                    'T1': schema_defs.tanf.t1,
+                    'T2': schema_defs.tanf.t2,
+                    'T3': schema_defs.tanf.t3,
+                },
+                'C': {
+                    'T4': schema_defs.tanf.t4,
+                    'T5': schema_defs.tanf.t5,
+                },
+                'G': {
+                    'T6': schema_defs.tanf.t6,
+                },
+                'S': {
+                    'T7': schema_defs.tanf.t7,
+                },
+            }
+        case 'SSP':
+            return {
+                'A': {
+                    'M1': schema_defs.ssp.m1,
+                    'M2': schema_defs.ssp.m2,
+                    'M3': schema_defs.ssp.m3,
+                },
+                'C': {
+                    # 'M4': schema_options.m4,
+                    # 'M5': schema_options.m5,
+                },
+                'G': {
+                    # 'M6': schema_options.m6,
+                },
+                'S': {
+                    # 'M7': schema_options.m7,
+                },
+            }
+        # case tribal?
+    return None
+
+
 def get_schema_manager(line, section, program_type):
     """Return the appropriate schema for the line."""
     line_type = line[0:2]

tdrs-backend/tdpservice/parsers/schema_defs/tanf/__init__.py

@@ -4,10 +4,12 @@
 from .t4 import t4
 from .t5 import t5
 from .t6 import t6
+from .t7 import t7
 
 t1 = t1
 t2 = t2
 t3 = t3
 t4 = t4
 t5 = t5
 t6 = t6
+t7 = t7

tdrs-backend/tdpservice/parsers/schema_defs/tanf/t7.py

@@ -0,0 +1,65 @@
+"""Schema for TANF T7 Row."""
+
+from ...util import SchemaManager
+from ...fields import Field, TransformField
+from ...row_schema import RowSchema
+from ...transforms import calendar_quarter_to_rpt_month_year
+from ... import validators
+from tdpservice.search_indexes.models.tanf import TANF_T7
+
+schemas = []
+
+validator_index = 7
+section_ind_index = 7
+stratum_index = 8
+families_index = 10
+for i in range(1, 31):
+    month_index = (i - 1) % 3
+    sub_item_labels = ['A', 'B', 'C']
+    families_value_item_number = f"6{sub_item_labels[month_index]}"
+
+    schemas.append(
+      RowSchema(
+          model=TANF_T7,
+          quiet_preparser_errors=i > 1,
+          preparsing_validators=[
+              validators.notEmpty(0, 7),
+              validators.notEmpty(validator_index, validator_index + 24),
+          ],
+          postparsing_validators=[],
+          fields=[
+              Field(item="0", name="RecordType", type='string', startIndex=0, endIndex=2,
+                    required=True, validators=[]),
+              Field(item="3", name='CALENDAR_QUARTER', type='number', startIndex=2, endIndex=7,
+                    required=True, validators=[validators.dateYearIsLargerThan(1998),
+                                               validators.quarterIsValid()]),
+              TransformField(
+                  transform_func=calendar_quarter_to_rpt_month_year(month_index),
+                  item="3A",
+                  name='RPT_MONTH_YEAR',
+                  type='number',
+                  startIndex=2,
+                  endIndex=7,
+                  required=True,
+                  validators=[
+                      validators.dateYearIsLargerThan(1998),
+                      validators.dateMonthIsValid()
+                  ]
+              ),
+              Field(item="4", name='TDRS_SECTION_IND', type='string', startIndex=section_ind_index,
+                    endIndex=section_ind_index + 1, required=True, validators=[validators.oneOf(['1', '2'])]),
+              Field(item="5", name='STRATUM', type='string', startIndex=stratum_index,
+                    endIndex=stratum_index + 2, required=True, validators=[validators.isInStringRange(1, 99)]),
+              Field(item=families_value_item_number, name='FAMILIES_MONTH', type='number', startIndex=families_index,
+                    endIndex=families_index + 7, required=True, validators=[validators.isInLimits(0, 9999999)]),
+          ]
+      )
+    )
+
+    index_offset = 0 if i % 3 != 0 else 24
+    validator_index += index_offset
+    section_ind_index += index_offset
+    stratum_index += index_offset
+    families_index += 7 if i % 3 != 0 else 10
+
+t7 = SchemaManager(schemas=schemas)

tdrs-backend/tdpservice/parsers/test/data/ADS.E2J.FTP4.TS06

@@ -0,0 +1,3 @@
+HEADER20204S06   TAN1 N
+T720204101006853700680540068454103000312400037850003180104000347400036460003583106000044600004360000325299000506200036070003385202000039100002740000499                                                                                                
+TRAILER0000001         

tdrs-backend/tdpservice/parsers/test/factories.py

@@ -335,3 +335,17 @@ class Meta:
     NUM_BIRTHS = 1
     NUM_OUTWEDLOCK_BIRTHS = 1
     NUM_CLOSED_CASES = 1
+
+class TanfT7Factory(factory.django.DjangoModelFactory):
+    """Generate TANF T7 record for testing."""
+
+    class Meta:
+        """Hardcoded meta data for TANF_T7."""
+
+        model = "search_indexes.TANF_T7"
+
+    CALENDAR_QUARTER = 20204
+    RPT_MONTH_YEAR = 202011
+    TDRS_SECTION_IND = '1'
+    STRATUM = '01'
+    FAMILIES_MONTH = 1

tdrs-backend/tdpservice/parsers/test/test_parse.py

@@ -4,7 +4,7 @@
 import pytest
 from .. import parse
 from ..models import ParserError, ParserErrorCategoryChoices, DataFileSummary
-from tdpservice.search_indexes.models.tanf import TANF_T1, TANF_T2, TANF_T3, TANF_T4, TANF_T5, TANF_T6
+from tdpservice.search_indexes.models.tanf import TANF_T1, TANF_T2, TANF_T3, TANF_T4, TANF_T5, TANF_T6, TANF_T7
 from tdpservice.search_indexes.models.ssp import SSP_M1, SSP_M2, SSP_M3
 from .factories import DataFileSummaryFactory
 from tdpservice.data_files.models import DataFile
@@ -833,3 +833,32 @@ def test_parse_tanf_section3_file(tanf_section3_file):
     assert first.NUM_CLOSED_CASES == 3884
     assert second.NUM_CLOSED_CASES == 3881
     assert third.NUM_CLOSED_CASES == 5453
+
+@pytest.fixture
+def tanf_section4_file(stt_user, stt):
+    """Fixture for ADS.E2J.FTP4.TS06."""
+    return util.create_test_datafile('ADS.E2J.FTP4.TS06', stt_user, stt, "Stratum Data")
+
+@pytest.mark.django_db()
+def test_parse_tanf_section4_file(tanf_section4_file):
+    """Test parsing TANF Section 4 submission."""
+    parse.parse_datafile(tanf_section4_file)
+
+    assert TANF_T7.objects.all().count() == 18
+
+    parser_errors = ParserError.objects.filter(file=tanf_section4_file)
+    assert parser_errors.count() == 0
+
+    t7_objs = TANF_T7.objects.all().order_by('FAMILIES_MONTH')
+
+    first = t7_objs.first()
+    sixth = t7_objs[5]
+
+    assert first.RPT_MONTH_YEAR == 202011
+    assert sixth.RPT_MONTH_YEAR == 202012
+
+    assert first.TDRS_SECTION_IND == '2'
+    assert sixth.TDRS_SECTION_IND == '2'
+
+    assert first.FAMILIES_MONTH == 274
+    assert sixth.FAMILIES_MONTH == 499

tdrs-backend/tdpservice/parsers/util.py

@@ -129,7 +129,7 @@ def get_schema_options(program, section, query=None, model=None, model_name=None
             'S': {
                 'section': DataFile.Section.STRATUM_DATA,
                 'models': {
-                    # 'T7': schema_defs.tanf.t7,
+                    'T7': schema_defs.tanf.t7,
                 }
             }
         },

tdrs-backend/tdpservice/scheduling/parser_task.py

@@ -23,6 +23,10 @@ def parse(data_file_id):
     dfs = DataFileSummary.objects.create(datafile=data_file, status=DataFileSummary.Status.PENDING)
     errors = parse_datafile(data_file)
     dfs.status = dfs.get_status()
-    dfs.case_aggregates = case_aggregates_by_month(data_file, dfs.status)
+
+    if "Case Data" in data_file.section:
+        dfs.case_aggregates = case_aggregates_by_month(data_file, dfs.status)
+
     dfs.save()
+
     logger.info(f"Parsing finished for file -> {repr(data_file)} with status {dfs.status} and {len(errors)} errors.")

tdrs-backend/tdpservice/search_indexes/admin/tanf.py

@@ -109,12 +109,17 @@ class TANF_T7Admin(admin.ModelAdmin):
     """ModelAdmin class for parsed T7 data files."""
 
     list_display = [
-        'record',
-        'rpt_month_year',
+        'RecordType',
+        'CALENDAR_QUARTER',
+        'RPT_MONTH_YEAR',
+        'TDRS_SECTION_IND',
+        'STRATUM',
+        'FAMILIES_MONTH',
         'datafile',
     ]
 
     list_filter = [
+        'CALENDAR_QUARTER',
         CreationDateFilter,
-        'rpt_month_year',
+        'RPT_MONTH_YEAR',
     ]

tdrs-backend/tdpservice/search_indexes/documents/tanf.py

@@ -343,11 +343,10 @@ class Django:
 
         model = TANF_T7
         fields = [
-            'record',
-            'rpt_month_year',
-            'fips_code',
-            'calendar_quarter',
-            'tdrs_section_ind',
-            'stratum',
-            'families',
+            "RecordType",
+            "CALENDAR_QUARTER",
+            "RPT_MONTH_YEAR",
+            "TDRS_SECTION_IND",
+            "STRATUM",
+            "FAMILIES_MONTH",
         ]